diff --git a/pydata-global-2020/category.json b/pydata-global-2020/category.json
new file mode 100644
index 000000000..5a561492c
--- /dev/null
+++ b/pydata-global-2020/category.json
@@ -0,0 +1,3 @@
+{
+  "title": "PyData Global 2020"
+}
diff --git a/pydata-global-2020/videos/aileen-nielsen-open-source-fairness-pydata-global-2020.json b/pydata-global-2020/videos/aileen-nielsen-open-source-fairness-pydata-global-2020.json
new file mode 100644
index 000000000..0e2431315
--- /dev/null
+++ b/pydata-global-2020/videos/aileen-nielsen-open-source-fairness-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nFairness is a hot topic in AI/machine learning/technology these days, but there isn\u2019t much clear guidance on how to operationalize it into actual code. This talk will walk the audience through a few basic fairness algorithms and their open source implementations. We will also review recent developments in both the engineering and law of machine learning fairness.\n\nSpeaker\nAileen is a software engineer and data analyst with a data background that runs the gamut from experimental physics to healthcare startups to finance. She is the author of two O\u2019Reilly Media titles, Practical Time Series Analysis and Practical Fairness (forthcoming 2020), and frequently speaks and teaches at industry conferences around the world on her two areas of interest, time series forecasting and algorithmic fairness.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 2085,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Aileen Nielsen"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/UWysLJ93h3k/maxresdefault.webp",
+  "title": "Open Source Fairness",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=UWysLJ93h3k"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/akshay-bahadur-indian-sign-language-recognition-islar-pydata-global-2020.json b/pydata-global-2020/videos/akshay-bahadur-indian-sign-language-recognition-islar-pydata-global-2020.json
new file mode 100644
index 000000000..c3b6017e1
--- /dev/null
+++ b/pydata-global-2020/videos/akshay-bahadur-indian-sign-language-recognition-islar-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nIndia is a diverse country with regional diversification in spoken languages and scripts that are well known and widely documented, apparently, this has percolated in sign language as well, essentially resulting in multiple sign languages across the country. To help overcome these inconsistencies and to standardize sign language, I have developed an Indian Sign Language Recognition System (ISLAR).\n\nSpeaker\nAkshay Bahadur\u2019s interest in computer science sparked when he was working on a women\u2019s safety application aimed towards the women\u2019s welfare in India and since then he has been incessantly tackling social issues in India through technology. He is currently working alongside Google to make an Indian sign language recognition system (ISLAR) specifically aimed at running on low resource environments for developing countries. His ambition is to make valuable contributions towards the ML community and leave a message of perseverance and tenacity.\n\nHe\u2019s one out of 8 Google Developers Expert (Machine Learning) from India along with being one of 150 members worldwide for the Intel Software Innovator program.\n\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 488,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Akshay Bahadur"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/XI2nXwzGTAk/maxresdefault.webp",
+  "title": "Indian Sign Language Recognition (ISLAR)",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=XI2nXwzGTAk"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/alex-glaser-using-algorithm-x-to-reanalyse-the-last-uk-general-election-pydata-global-2020.json b/pydata-global-2020/videos/alex-glaser-using-algorithm-x-to-reanalyse-the-last-uk-general-election-pydata-global-2020.json
new file mode 100644
index 000000000..830ca338d
--- /dev/null
+++ b/pydata-global-2020/videos/alex-glaser-using-algorithm-x-to-reanalyse-the-last-uk-general-election-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nDonald Knuth\u2019s Algorithm X is a tried-and-tested technique to find solutions for the \u2018Exact Cover\u2019 problem, e.g. Sudoku. We\u2019ll give a brief overview of this algorithm and use it to re-analyse the results from the last UK general election using alternative voting systems.\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1852,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Alex Glaser"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/Myh7lepP9ss/maxresdefault.webp",
+  "title": "Using Algorithm X to reanalyse the last UK general election",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=Myh7lepP9ss"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/alexander-hendorf-better-code-for-data-science-pydata-global-2020.json b/pydata-global-2020/videos/alexander-hendorf-better-code-for-data-science-pydata-global-2020.json
new file mode 100644
index 000000000..07431c21a
--- /dev/null
+++ b/pydata-global-2020/videos/alexander-hendorf-better-code-for-data-science-pydata-global-2020.json
@@ -0,0 +1,32 @@
+{
+  "description": "Talk \nThe coding quality must be improved in Data Science and AI. Though code in notebooks may provide some working solutions, too often it\u2019s hard to maintain, reuse or even to read for an outsider - apart from being inefficient. In this talk I will share a decade of Python experience and provide background, good practices and guidelines that enable everyone to write proper code for Data & AI.\n\nSpeaker \nAlexander\u2019 professional career was always about digitalization: starting from vinyl records in the nineties to advanced data analytics nowadays.\n\nHe\u2019s a PyData organiser (Frankfurt and S\u00fcdwest), a Python Software Foundation fellow, emeritus program chair of EuroPython, PyConDE & PyData Berlin 2019/20 and the scientific Python conference EuroSciPy. He\u2019s one of the 25 mongoDB masters and a regular contributor to the tech community. As regular speaker at international conferences in he love to talk about, discuss and train tech. Being a partner at K\u00f6nigsweg (https://koenisgweg.com) - a boutique Data Science and AI consultancy based in Mannheim, Germany - he\u2019s advising and training industry clients in AI, data science, data literacy and big data matters.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 2429,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    },
+    {
+      "label": "https://koenisgweg.com",
+      "url": "https://koenisgweg.com"
+    }
+  ],
+  "speakers": [
+    "Alexander Hendorf"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/68L00cvYXXQ/maxresdefault.webp",
+  "title": "Better Code for Data Science",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=68L00cvYXXQ"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/andrew-weeks-building-fairer-models-for-finance-pydata-global-2020.json b/pydata-global-2020/videos/andrew-weeks-building-fairer-models-for-finance-pydata-global-2020.json
new file mode 100644
index 000000000..832c064e1
--- /dev/null
+++ b/pydata-global-2020/videos/andrew-weeks-building-fairer-models-for-finance-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talks\nFairness and bias are rightly hot topics in ML because of their impact on people\u2019s lives. It\u2019s particularly important in finance, where bad decisions can limit the ability to participate in society. We look at how fairness can be defined, and how the law defines it. We explore how to detect bias, the trade off between bias and performance, and how to build fairer models that still perform well.\n\nSpeaker\nI\u2019m a product-focused data scientist at Aire, a fintech startup and credit reference agency. I\u2019ve been part of the startup scene in London for nearly a decade.\n\nAt Aire I\u2019ve been responsible for shaping products for the UK and US markets from an early stage, building credit risk models and other insights, and worked closely on our governance framework and fairness processes.\n\nI try to spend as much time as I can on understanding the problem. It\u2019s usually a lot messier and more complex than I realise, but it\u2019s key to building solutions that have a real impact!\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1819,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Andrew Weeks"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/TQjJdHA4Kfg/maxresdefault.webp",
+  "title": "Building fairer models for finance",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=TQjJdHA4Kfg"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/andy-terrel-how-to-review-a-model-pydata-global-2020.json b/pydata-global-2020/videos/andy-terrel-how-to-review-a-model-pydata-global-2020.json
new file mode 100644
index 000000000..6e316be48
--- /dev/null
+++ b/pydata-global-2020/videos/andy-terrel-how-to-review-a-model-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nModels have become the high risk credit card of technical debt. In this talk, we discuss how to pay down that credit card with good model review practices\n\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 2143,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Andy Terrel"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/IwE6S2dvgfQ/maxresdefault.webp",
+  "title": "How to review a model",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=IwE6S2dvgfQ"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/ankit-mahato-supercharge-scientific-computing-in-python-with-numba-pydata-global-2020.json b/pydata-global-2020/videos/ankit-mahato-supercharge-scientific-computing-in-python-with-numba-pydata-global-2020.json
new file mode 100644
index 000000000..1ea1b947c
--- /dev/null
+++ b/pydata-global-2020/videos/ankit-mahato-supercharge-scientific-computing-in-python-with-numba-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nPython is the goto language for computational research, but often we are hit by the performance bottleneck of this language. In this talk, we will delve into 3 real-world computational exercises to introduce the core concepts, ease & effectiveness of using Numba, a JIT compiler that translates Python & NumPy code into fast machine code. Let\u2019s supercharge our scientific computing research today!\n\nSpeaker\nA die hard Pythonista, Ankit is an open source contributor and a former Google Summer of Code scholar under Python Software Foundation. Currently, he is working in the domain of scientific computing and Machine Learning in IoT devices.\n\nAnkit has 6 years of industrial experience (Associate - JP Morgan, Data Scientist & Product Manager - Fuzzy Logix, USA) in machine learning, quantitative modelling, data analytics and visualization. Over the years, he has developed an expertise in handling the entire data analytics pipeline comprising \u2013 ingestion, exploration, transformation, modeling and deployment. He is a polyglot programmer with an extensive knowledge of algorithms, statistics and parallel programming. He has shipped multiple releases of DB Lytix, a comprehensive library of over 800 mathematical and statistical functions used widely in data mining, machine learning and analytics applications, including \u201cbig data analytics\u201d.\n\nAn IIT Kanpur alumnus, Ankit is also an active researcher with publications on scientific computing in international journal and conferences. He is actively working in the domain of Analytics and has presented his work in:\n\nPyCon India 2019 (Talk)\n5th International Conference on Data Science and Engineering 2019\nData Science Congress 2018\n5th IIMA International Conference on Advanced Data Analysis, Business Analytics and Intelligence 2017\nSciPy India 2017 (Talk) \nHe is also an active contributor to the Indian Python Community and has conducted 5 workshops in PyCon India 2017 & 2019 and Scipy India 2017, 2018 & 2019.\nPublications - Link \nLinkedIn - Link \nAcclaim Badges - Link\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1291,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Ankit Mahato"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/mDsTkg_IpUk/maxresdefault.webp",
+  "title": "Supercharge Scientific Computing in Python with Numba",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=mDsTkg_IpUk"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/anne-devan-song-pythons-in-python-wildlife-trade-data-analysis-using-python-pydata-global-2020.json b/pydata-global-2020/videos/anne-devan-song-pythons-in-python-wildlife-trade-data-analysis-using-python-pydata-global-2020.json
new file mode 100644
index 000000000..f876dbc83
--- /dev/null
+++ b/pydata-global-2020/videos/anne-devan-song-pythons-in-python-wildlife-trade-data-analysis-using-python-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nI am a data scientist and field biologist with research interests in social ecological systems. I am a PhD candidate at Oregon State University, co-advised in disease ecology and social-environmental analysis labs. For my PhD, I am using network analytic tools to understand properties of wildlife and human-wildlife collectives, through a lens of disease spread and conservation. I am particularly interested in the integration of field biology methods with computational approaches to solve real-world conservation problems.\n\nI am originally from Singapore, and now live in Corvallis, Oregon, USA, where I love cycling, hiking, climbing, and cooking. You can read more about me on my website.\n\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 443,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Anne Devan Song"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/H0S12tiglW8/maxresdefault.webp",
+  "title": "Pythons in Python: Wildlife Trade Data Analysis Using Python",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=H0S12tiglW8"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/arnaud-van-looveren-monitoring-machine-learning-models-in-production-pydata-global-2020.json b/pydata-global-2020/videos/arnaud-van-looveren-monitoring-machine-learning-models-in-production-pydata-global-2020.json
new file mode 100644
index 000000000..f9cdea682
--- /dev/null
+++ b/pydata-global-2020/videos/arnaud-van-looveren-monitoring-machine-learning-models-in-production-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nMonitoring deployed models is crucial for continued provisioning of high quality ML enabled services. Key areas include model performance monitoring, detecting adversarial instances, outliers and drift using statistical techniques. The talk goes in depth on the algorithmic challenges to monitor models in production and the open source libraries and infrastructure to support these capabilities.\n\nSpeaker\nArnaud leads the data science research effort at Seldon Technologies, focusing on machine learning model interpretability (XAI), outlier, adversarial and drift detection. The team\u2019s work can be found in open source projects Alibi and Alibi Detect. Arnaud recently discussed challenges around monitoring and explaining models in production at the \u201cChallenges in Deploying and Monitoring Machine Learning Systems\u201d workshop at ICML.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1861,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Arnaud Van Looveren"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/fn9Ks9SO2tI/maxresdefault.webp",
+  "title": "Monitoring machine learning models in production",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=fn9Ks9SO2tI"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/ben-fowler-chelsey-meise-openingtheblackbox-pydata-global-2020.json b/pydata-global-2020/videos/ben-fowler-chelsey-meise-openingtheblackbox-pydata-global-2020.json
new file mode 100644
index 000000000..2109cb5f6
--- /dev/null
+++ b/pydata-global-2020/videos/ben-fowler-chelsey-meise-openingtheblackbox-pydata-global-2020.json
@@ -0,0 +1,29 @@
+{
+  "description": "Talk \nData scientists have likely heard that machine learning models are \u2018black boxes\u2019 and not interpretable. This notion, once formerly true, is no longer correct. In this talk, the modelers at Southeast Toyota Finance will focus on model-agnostic interpretability techniques. We\u2019ll provide an end-to-end example of the experimentation process of modeling combined with interpretability techniques.\n\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1711,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Ben Fowler",
+    "Chelsey Meise"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/8lwfGf7HAEc/maxresdefault.webp",
+  "title": "OpeningTheBlackBox",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=8lwfGf7HAEc"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/bogumil-kaminski-an-introduction-to-dataframes-for-pandas-users-pydata-global-2020.json b/pydata-global-2020/videos/bogumil-kaminski-an-introduction-to-dataframes-for-pandas-users-pydata-global-2020.json
new file mode 100644
index 000000000..dc86ce8be
--- /dev/null
+++ b/pydata-global-2020/videos/bogumil-kaminski-an-introduction-to-dataframes-for-pandas-users-pydata-global-2020.json
@@ -0,0 +1,32 @@
+{
+  "description": "Talk \nIn this talk I present the fundamental design concepts behind DataFrames.jl to help potential users get started with using it. I show how an exemplary pandas data processing pipeline can be transferred to DataFrames.jl. Finally I discuss how DataFrames.jl integrates with the whole data science ecosystem available in the Julia language.\n\nSpeaker \nI am a researcher in the fields of operations research and computational social science. During the last several years I have significantly contributed to the data science packages for the Julia language. In particular, I am one of the core developers of the DataFrames.jl package.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. \n\n00:00 Welcome!\n00:15 Why use DataFrames.jl\n4:19 - Hands-on working with DataFrames in Julia\n8:05 - Reading a DataFrame\n10:29 - Simple operations on a DataFrame (Julia vs Pandas)\n21:37 - Aggregation functions\n25:35 - Piping\n27:17 - Noteworthy packages in the Julia Ecosystem\n\nS/o to https://github.com/stobinaator for the video timestamps!\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1810,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    },
+    {
+      "label": "https://github.com/stobinaator",
+      "url": "https://github.com/stobinaator"
+    }
+  ],
+  "speakers": [
+    "Bogumił Kamiński"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/K2J8pwSyUMw/maxresdefault.webp",
+  "title": "An introduction to DataFrames for pandas users",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=K2J8pwSyUMw"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/brian-lucas-enquiry-based-learning-for-science-and-engineering-utilizing-bokeh-pydata-global-2020.json b/pydata-global-2020/videos/brian-lucas-enquiry-based-learning-for-science-and-engineering-utilizing-bokeh-pydata-global-2020.json
new file mode 100644
index 000000000..eed3ba3d5
--- /dev/null
+++ b/pydata-global-2020/videos/brian-lucas-enquiry-based-learning-for-science-and-engineering-utilizing-bokeh-pydata-global-2020.json
@@ -0,0 +1,32 @@
+{
+  "description": "Talk\nComputational modules are valuable pedagogical tools to teach complex engineering concepts via enquiry-based learning (EBL). In this context, we have developed interactive online visualization-based python modules to explain science and engineering concepts through common chemical engineering applications. All these modules can be accessed at this website: https://srrweb.cc.lehigh.edu/app/.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 597,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    },
+    {
+      "label": "https://srrweb.cc.lehigh.edu/app/.",
+      "url": "https://srrweb.cc.lehigh.edu/app/."
+    }
+  ],
+  "speakers": [
+    "Brian Lucas"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/v_T3jRRwHnQ/maxresdefault.webp",
+  "title": "Enquiry Based Learning for Science and Engineering utilizing Bokeh",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=v_T3jRRwHnQ"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/cameron-davidson-pilon-a-crash-update-to-lifelines-pydata-global-2020.json b/pydata-global-2020/videos/cameron-davidson-pilon-a-crash-update-to-lifelines-pydata-global-2020.json
new file mode 100644
index 000000000..320b2af75
--- /dev/null
+++ b/pydata-global-2020/videos/cameron-davidson-pilon-a-crash-update-to-lifelines-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \n\nlifelines, the popular Python survival analysis library, has come a long way since its release in 2013, and development has accelerated these past two years. In this crash-update, I will demonstrate some of the newest features of lifelines in the past two years, our philosophy of \u201cmake the current best practice easy\u201d, and what\u2019s to come in lifelines as we plan our first 1.x release.\n\nSpeaker\nCameron Davidson-Pilon has worked in many areas of applied statistics, from the evolutionary dynamics of genes to modelling of financial prices. His contributions to the community include lifelines, an implementation of survival analysis in Python, lifetimes, and Bayesian Methods for Hackers, an open source book & printed book on Bayesian analysis. Formally director of data science at Shopify, Cameron is now applying data science to the alt-protein space.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 317,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Cameron Davidson-Pilon"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/KQMaNpo3qBE/maxresdefault.webp",
+  "title": "A crash-update to lifelines",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=KQMaNpo3qBE"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/chin-hwee-ong-speed-up-your-data-processing-pydata-global-2020.json b/pydata-global-2020/videos/chin-hwee-ong-speed-up-your-data-processing-pydata-global-2020.json
new file mode 100644
index 000000000..8b784c8ea
--- /dev/null
+++ b/pydata-global-2020/videos/chin-hwee-ong-speed-up-your-data-processing-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nConstantly waiting for your data processing code to finish executing? Through real-life stories and analogies, we will explore how to leverage on parallel and asynchronous programming in Python to speed up your data processing pipelines - so that you could focus more on getting value out of your data.\n\n\nSpeaker\nChin Hwee Ong is a data engineer, aspiring polymath and Industry 4.0 enthusiast who happens to have a background in aerospace engineering and computational modelling. As an avid user of the pandas library and a beneficiary of open source, Chin Hwee enjoys sharing about data manipulation using pandas and has a not-so-secret wish for data processing codes to run faster.\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1818,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Chin Hwee Ong"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/E9sv2B3Bb20/maxresdefault.webp",
+  "title": "Speed Up Your Data Processing",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=E9sv2B3Bb20"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/christopher-lozinski-crowdsource-a-distributed-organizations-data-model-pydata-global-2020.json b/pydata-global-2020/videos/christopher-lozinski-crowdsource-a-distributed-organizations-data-model-pydata-global-2020.json
new file mode 100644
index 000000000..1b92dbb0d
--- /dev/null
+++ b/pydata-global-2020/videos/christopher-lozinski-crowdsource-a-distributed-organizations-data-model-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk\nMembers of the United States Green Party, working for the Howie Hawkins presidential campaign, and numerous state parties, are crowdsourcing a map of the United States Green Party politicians, organizations and events. It is not just a map, it is an object model of the organization, running on a hierarchical object-graph database.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 535,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Christopher Lozinski"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/AaRqUTg0Wmk/maxresdefault.webp",
+  "title": "Crowdsource a Distributed Organizations Data Model",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=AaRqUTg0Wmk"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/christopher-rackauckas-accelerating-differential-equations-in-r-and-python-pydata-global-2020.json b/pydata-global-2020/videos/christopher-rackauckas-accelerating-differential-equations-in-r-and-python-pydata-global-2020.json
new file mode 100644
index 000000000..c80e497db
--- /dev/null
+++ b/pydata-global-2020/videos/christopher-rackauckas-accelerating-differential-equations-in-r-and-python-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nWhile Python libraries like SciPy commonly use C and Fortran code under the hood, could Julia be used in the same way? In this talk we\u2019ll introduce diffeqpy, a Julia-accelerated Python library for solving differential equations orders of magnitude faster than JIT-accelerated SciPy. We will discuss how it was built and how the unique tools like ModelingToolkit.jl help Python scientists.\n\nSpeaker \nChris Rackauckas is an Applied Mathematics Instructor at MIT, a Senior Research Analyst in the University of Maryland, Baltimore School of Pharmacy, and Director of Scientific Research at Pumas-AI. He is the lead developer of the SciML open source scientific machine learning organization which develops widely used software for scientific modeling and inference such as DifferentialEquations.jl for which he won the inaugural Julia Community Prize. Chris\u2019 work on high performance differential equation solving is the centerpiece accelerating many applications from the MIT-CalTech CLiMA climate modeling initiative to the SIAM Dynamical Systems award winning DynamicalSystems.jl toolbox. Chris is the lead developer of Pumas, the FDA-compliant foundational software of Pumas-AI for nonlinear mixed effects modeling in clinical pharmacology which has had notable partnerships with leading pharmaceutical companies such as Pfizer. These efforts on Pumas led to the International Society of Pharmacology\u2019s (ISoP) Mathematical and Computational Special Interest Group Award at the American Conference of Pharmacology (ACoP) 2019. His PhD research at UC Irvine focused on the control of intrinsic stochasticity in biological and pharmacological systems for which his thesis won the Kovalesvsky Outstanding Thesis Award and he was a recipient of the Mathematical and Computational Biology institutional fellowship, the Graduate Dean\u2019s Fellowship, the National Science Foundation\u2019s Graduate Research Fellowship, the NIH T32 Predoctural Training Grant, and the Data Science Initiative Summer Fellowship.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 2178,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Christopher Rackauckas"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/Jf2VUGaPL4k/maxresdefault.webp",
+  "title": "Accelerating Differential Equations In R and Python",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=Jf2VUGaPL4k"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/colleen-m-farrelly-lessons-from-a-nuclear-core-loading-quantum-algorithm-study-pydata-global-2020.json b/pydata-global-2020/videos/colleen-m-farrelly-lessons-from-a-nuclear-core-loading-quantum-algorithm-study-pydata-global-2020.json
new file mode 100644
index 000000000..e42e642fa
--- /dev/null
+++ b/pydata-global-2020/videos/colleen-m-farrelly-lessons-from-a-nuclear-core-loading-quantum-algorithm-study-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nThis talk presents lessons learned from an initial, novel application of quantum and quantum-inspired machine learning algorithms to optimize core loading patterns. Some of the challenges faced have included performance concerns on large simulation problems, lack of quality open-source code for some target algorithms, and the need for software interactions with a proprietary software.\n\nSpeaker\nColleen M. Farrelly is an experienced data scientist and entrepreneur whose expertise spans many industries, including quantum computing, nuclear engineering, education, defense, healthcare, and biotech. Her research focuses on topological data analysis, psychometrics, network analytics, and quantum machine learning. She\u2019s currently working on a book focused on applications of topology and geometry to machine learning.\n\n\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 429,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Colleen M. Farrelly"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/CuOl2eJ9Mmw/maxresdefault.webp",
+  "title": "Lessons From A Nuclear Core Loading Quantum Algorithm Study",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=CuOl2eJ9Mmw"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/dipam-paul-ensemble-x-your-personal-stratagem-to-build-ensemble-pydata-global-2020.json b/pydata-global-2020/videos/dipam-paul-ensemble-x-your-personal-stratagem-to-build-ensemble-pydata-global-2020.json
new file mode 100644
index 000000000..1603ff7de
--- /dev/null
+++ b/pydata-global-2020/videos/dipam-paul-ensemble-x-your-personal-stratagem-to-build-ensemble-pydata-global-2020.json
@@ -0,0 +1,29 @@
+{
+  "description": "Talk \nIn this talk, we will deep dive into the world of Medical Imaging and Radiology, in particular. We will soar through the mighty oceans of various kinds of diseases and limitations of AI with the prevalent Deep Learning architectures which are at our disposal. At this point, we will also delve into the progress that has been made in the domain of integrative healthcare.\n\nSpeakers\nCommonly referred to as \u2018The Boy from Kolkata\u2019 - Dipam is a final-year student pursuing Electronics and Telecommunication from KIIT University, India. He has previously presented at three PyCons-\n\n(1) PyCon USA 2019 (Cleveland, Ohio) [Speaker Profile]\n\n(2) PyCon India 2019 (Chennai, India) [Speaker Profile]\n\n(3) PyCon USA 2020 (Pittsburgh, Pennsylvania) [Speaker Profile]\n\n(4) PyCon Australia 2020 (Adelaide, Australia) [Speaker Profile]\n\nCurrently, he is an incoming Research Assistant at Stanford Medicine and will be working on areas of Radiology and Pain operating from the city of California.\n\nHe has previously worked in labs at Georgia Institute of Technology, Universidade Federal de Sao Paulo and IIT Bombay in various roles and capacities.\n\nHaving always been fascinated by the wonders one can do using Python, his periphery of interest lies in Biomedical-Imaging and NLP. He spends his days toying around with Machine-Learning models and fine-tuning Neural Nets when he is not eating, raconteuring or engaging in a lively debate about Geopolitics or Football!\n\nHailing from a small town called Lucknow, in India, Alankrita is a final year student at KIIT University. She started exploring Python recently and have been smitten by it ever since. She believes that the sky is the limit when it comes to what can be done with Python.\n\nSince then, she has presented her research in conferences like - PyCon US 2020 PyCon Australia 2020 IEEE 33rd International Symposium on Computer Based Medical Systems (CBMS) And she hopes to continue doing so.\n\nIn her spare time she is found reading, dreaming about seemingly impossible sci-fi scenarios (like the time she thought of using magnetic boots to levitate) and petting every dog she sees.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1864,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Dipam Paul",
+    "Alankrita"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/7nalY3_eDpA/maxresdefault.webp",
+  "title": "Ensemble X Your personal strataGEM to build Ensemble",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=7nalY3_eDpA"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/elle-o-brien-devops-for-science-using-continuous-integration-pydata-global-2020.json b/pydata-global-2020/videos/elle-o-brien-devops-for-science-using-continuous-integration-pydata-global-2020.json
new file mode 100644
index 000000000..d2d50cdff
--- /dev/null
+++ b/pydata-global-2020/videos/elle-o-brien-devops-for-science-using-continuous-integration-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nContinuous integration is a key practice from DevOps that encourages frequent code check-ins and testing in a production-like environment. While continuous integration is typically associated with speeding up development cycles for software, it also provides a rigorous framework for automating analysis, modeling, and reporting data viz and statistical results that is desirable for open science.\n\nSpeaker \nDr. Elle O\u2019Brien is a data scientist at Iterative, Inc. (the team behind DVC and one of the creators of Continuous Machine Learning (CML), an open source project for advancing DevOps practices in data science. She holds a PhD from the University of Washington and has presented about data science, DevOps, and scientific methods at more than 25 academic and industry meetings. Previously, she conducted research in computational neuroscience and speech perception, and worked as the Chief Scientist at Botnik Studios, an AI-comedy writing collective.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1834,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Elle O'Brien"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/0MbX4ve6vpo/maxresdefault.webp",
+  "title": "DevOps for Science: using continuous integration",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=0MbX4ve6vpo"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/esteban-gabancho-data-processing-pipelines-for-small-big-data-pydata-global-2020.json b/pydata-global-2020/videos/esteban-gabancho-data-processing-pipelines-for-small-big-data-pydata-global-2020.json
new file mode 100644
index 000000000..bd1569966
--- /dev/null
+++ b/pydata-global-2020/videos/esteban-gabancho-data-processing-pipelines-for-small-big-data-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nSmall Big Data is a grey area in data science between \u201cit fits in memory\u201d and 100 Tb. Some of the tools used for big data are overkill, and they might require a particular set of expertise that not every organization has. In contrast, many of the libraries and paradigms used for small data can become expensive when deploying to the cloud. How can we process large-ish data fast and efficiently?\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 2077,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Esteban Gabancho"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/3Wg6ESafMxg/maxresdefault.webp",
+  "title": "Data Processing Pipelines for Small Big Data",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=3Wg6ESafMxg"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/gael-varoquaux-dirty-data-science-machine-learning-on-non-curated-data-pydata-global-2020.json b/pydata-global-2020/videos/gael-varoquaux-dirty-data-science-machine-learning-on-non-curated-data-pydata-global-2020.json
new file mode 100644
index 000000000..a3dcf7471
--- /dev/null
+++ b/pydata-global-2020/videos/gael-varoquaux-dirty-data-science-machine-learning-on-non-curated-data-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nCleaning data to analyze it is a major roadblock to data science. I will discuss two specific problems, missing values and categories which variants and typos, in the context of machine learning. This talk will be on recent publications but give simple solutions in Python.\n\nSpeaker\nI am a research director at Inria (French National Computer Science Research Institute), studying machine learning for health, as well as a visiting professor at McGill university. I have a strong academic track record in fundamental machine learning and mental health applications (many publications in the best venues such as NeurIPS and ICML, editor at elife, one of the reference life sciences journal).\n\nI have been a contributor to the numeric Python and pydata stack since the mid 2000s, contributing to numpy, Mayavi, and later founding scikit-learn and joblib, as well as a few other domain-specific packages.\n\nI have been talking about Python and data processing and teaching it for 15 years. I helped creating and curating the scipy lecture notes, and gave many tutorials as well as keynotes at various Python conferences.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1765,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Gael Varoquaux"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/BsDeG3jQ61s/maxresdefault.webp",
+  "title": "Dirty Data Science Machine Learning On Non Curated Data",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=BsDeG3jQ61s"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/gajendra-deshpande-inventing-curriculum-using-python-and-spacy-pydata-global-2020.json b/pydata-global-2020/videos/gajendra-deshpande-inventing-curriculum-using-python-and-spacy-pydata-global-2020.json
new file mode 100644
index 000000000..4287b44af
--- /dev/null
+++ b/pydata-global-2020/videos/gajendra-deshpande-inventing-curriculum-using-python-and-spacy-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nIn this talk, attendees will learn about natural language processing techniques (spaCy) using Python and how it can be combined with machine learning(scikit-learn) to generate new knowledge from the existing knowledge. We will talk about how we designed curriculum using natural language processing, unsupervised machine learning and pointer-generator network.\n\n\nSpeaker\nI have delivered talks at SciPy India, PyCon FR, PyCon HK and JuliaCon. I use Python extensively for teaching and research. My major work includes using Python to develop prototypes in the field of Cyber Security. I lead PyData Belagavi and OWASP Belagavi chapters. I love to mentor students and volunteer at Free and Open Source events.\n\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1488,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Gajendra Deshpande"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/O6QeM_vC5KI/maxresdefault.webp",
+  "title": "Inventing Curriculum using Python and spaCy",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=O6QeM_vC5KI"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/hagit-grushka-what-cyber-security-can-teach-us-about-covid-19-testing-pydata-global-2020.json b/pydata-global-2020/videos/hagit-grushka-what-cyber-security-can-teach-us-about-covid-19-testing-pydata-global-2020.json
new file mode 100644
index 000000000..a990541f1
--- /dev/null
+++ b/pydata-global-2020/videos/hagit-grushka-what-cyber-security-can-teach-us-about-covid-19-testing-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nBy using 10\u201320% of the testing capacity for Covid19 governments can learn about the virus spread in the population and act accordingly even while the testing capacity is still being built. This solution comes from a famous statistics problem, Multi-Armed Bandits.\n\nSpeaker \nHagit Grushka-Cohen is a PhD student at Ben-Gurion University, the department of software and information systems, under the supervision of prof. Lior Rokach and prof. Bracha Shapira. Her PhD topic at applied Machine Learning in the domain of cyber security. Hagit won the prestigious IBM fellowship award for her work on risk assessment and working towards automatic policy calibration twice. During her PhD Hagit collaborated with IBM Guardium and IBM, IBM Cyber Center of Excellence which led to several ML papers (including CIKM and PAKDD). Prior to starting her PhD Hagit was a project manager in Adama and a BI projects leader in Stanly works.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1355,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Hagit Grushka-Cohen"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/QHVl7lES5_4/maxresdefault.webp",
+  "title": "What cyber security can teach us about COVID-19 testing",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=QHVl7lES5_4"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/hank-doupe-taking-care-of-parameters-so-you-don-t-have-to-with-paramtools-pydata-global-2020.json b/pydata-global-2020/videos/hank-doupe-taking-care-of-parameters-so-you-don-t-have-to-with-paramtools-pydata-global-2020.json
new file mode 100644
index 000000000..ad3c2e750
--- /dev/null
+++ b/pydata-global-2020/videos/hank-doupe-taking-care-of-parameters-so-you-don-t-have-to-with-paramtools-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talks \nParamTools is a general purpose library for input processing and validation. It was created for the \u201ctaxing\u201d task of processing the inputs of Tax-Calculator, a model that uses one of the most complicated specifications of all: the US tax code. This talk will demonstrate how ParamTools provides a friendly API and how it helps wrangle inputs into data that can be used by your model.\n\nSpeaker \nHank is an open-source software developer and consultant at Compute Tooling. He created ParamTools, a library for parameter processing and validation, and co-created Compute Studio, a platform for running and sharing models and data visualizations. He is on the leadership council of the Policy Simulation Library (PSL) and a contributor to models in PSL like Tax-Calculator. Prior to joining Compute Tooling, Hank worked at the Open Source Policy Center, where he developed open-source public policy models and tools.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1756,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Hank Doupe"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/XQ85WfHgXWo/maxresdefault.webp",
+  "title": "Taking Care of Parameters So You Don't Have to with ParamTools",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=XQ85WfHgXWo"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/haris-pozidis-snap-ml-accelerated-accurate-efficient-machine-learning-pydata-global-2020.json b/pydata-global-2020/videos/haris-pozidis-snap-ml-accelerated-accurate-efficient-machine-learning-pydata-global-2020.json
new file mode 100644
index 000000000..b2888ee02
--- /dev/null
+++ b/pydata-global-2020/videos/haris-pozidis-snap-ml-accelerated-accurate-efficient-machine-learning-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nSnap ML is a library for machine learning training and inference offering a familiar python scikit-learn API. With Snap ML one can typically train ML models 10 times faster than with scikit-learn on CPU and/or GPU, and achieve similar speed-up in model inference. Additionally, powerful models such as boosting machines can be trained that often beat XGBoost or LightGBM in generalization accuracy.\n\nSpeaker\nHaris Pozidis manages the Data and AI Systems group at IBM Research in Zurich, Switzerland. He received a Ph.D. degree in electrical engineering from Drexel University, Philadelphia, USA, in 1998, and was with Philips Research, Eindhoven, The Netherlands, before joining IBM. He has worked on read channel design for DVD and Blu-ray Disc at Philips, and played a key role in developing the first scanning probe-based data storage system at IBM, the \u201cMillipede\u201d. His current focus is on the development of Flash memory controllers for all-flash arrays, on AI-infused solutions for IT operations, and on accelerated software libraries for machine learning. Haris holds over 130 US patents, has co-authored more than 120 publications, is an IBM Principal Research Scientist, an IBM Master Inventor, and a Senior Member of the IEEE.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1817,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Haris Pozidis"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/tkbOoHunsLk/maxresdefault.webp",
+  "title": "Snap ML: Accelerated, Accurate, Efficient, Machine Learning",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=tkbOoHunsLk"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/ian-ozsvald-skinny-pandas-riding-on-a-rocket-pydata-global-2020.json b/pydata-global-2020/videos/ian-ozsvald-skinny-pandas-riding-on-a-rocket-pydata-global-2020.json
new file mode 100644
index 000000000..8e6cccbe2
--- /dev/null
+++ b/pydata-global-2020/videos/ian-ozsvald-skinny-pandas-riding-on-a-rocket-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nWith larger datasets we need to be smarter about how we use Pandas to get results. We\u2019ll look at strategies to shrink our data to get more into RAM, offload computation to tools like Dask or Vaex, store with Parquet or SQLite, make calculations faster and retain debuggability.\n\nSpeaker \nIan is a Chief Data Scientist and Coach, he helps co-organise the annual PyDataLondon conference with 700+ attendees and the associated 11,000+ member monthly meetup. He runs the established Mor Consulting Data Science consultancy in London, gives conference talks internationally often as keynote speaker and is the author of the bestselling O\u2019Reilly book High Performance Python (2nd edition). He has 18 years of experience as a senior data science leader, trainer and team coach. For fun he\u2019s walked by his high-energy Springer Spaniel, surfs the Cornish coast and drinks fine coffee. Past talks and articles can be found at: IanOzsvald.com\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1953,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Ian Ozsvald"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/qsiUOXwexus/maxresdefault.webp",
+  "title": "Skinny Pandas Riding On A Rocket",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=qsiUOXwexus"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/irina-vidal-migallon-visual-data-abundant-relevant-labelled-cheap-pick-two-pydata-global-2020.json b/pydata-global-2020/videos/irina-vidal-migallon-visual-data-abundant-relevant-labelled-cheap-pick-two-pydata-global-2020.json
new file mode 100644
index 000000000..09b06c5b9
--- /dev/null
+++ b/pydata-global-2020/videos/irina-vidal-migallon-visual-data-abundant-relevant-labelled-cheap-pick-two-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nIn Computer Vision, we often find data is either never enough, or expensive to label, or not relevant to the problem. There isn\u2019t an Imagenet for every sensor. What tools can you use on little (or no) visual data, what purpose do they serve and what risks do they have?\n\nSpeaker \nElectrical Engineer & Biomedical Engineer who specialised in Machine Learning & Vision. Seasoned in different industries - from optical biopsy systems in France to surgical planning tools and Augmented Reality apps in the Berlin start-up scene-, she now works in Siemens Mobility\u2019s Computer Vision & AI team. Even more than waking up Skynet, she\u2019s interested in the limits of Natural Intelligence and its decisions over our data.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1816,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Irina Vidal Migallon"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/I5eOgv6Z714/maxresdefault.webp",
+  "title": "Visual data abundant relevant labelled cheap Pick two",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=I5eOgv6Z714"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/isabel-yepes-nlp-spanish-challenges-alternatives-pydata-global-2020.json b/pydata-global-2020/videos/isabel-yepes-nlp-spanish-challenges-alternatives-pydata-global-2020.json
new file mode 100644
index 000000000..513dad732
--- /dev/null
+++ b/pydata-global-2020/videos/isabel-yepes-nlp-spanish-challenges-alternatives-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nMost NLP is done in English; however almost 8% of internet users communicate in Spanish being the 3rd most-widely spoken language and the 2nd on social networks like Facebook and Twitter. Well know tools for NLP have no comprehensive corpus in Spanish or they are private. I present the challenges faced doing NLP in Spanish, alternatives and open a question about how community could help with this\n\nSpeaker\nElectronics Engineer with experience in IT Infrastructure, Networking and Software Development. Previous experience as Technical Instructor and Evangelist.\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 647,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Isabel Yepes"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/zP--hE2zoAg/maxresdefault.webp",
+  "title": "NLP Spanish Challenges Alternatives",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=zP--hE2zoAg"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/joel-grus-ten-ways-to-fizz-buzz-pydata-global-2020.json b/pydata-global-2020/videos/joel-grus-ten-ways-to-fizz-buzz-pydata-global-2020.json
new file mode 100644
index 000000000..54cd6bcbd
--- /dev/null
+++ b/pydata-global-2020/videos/joel-grus-ten-ways-to-fizz-buzz-pydata-global-2020.json
@@ -0,0 +1,32 @@
+{
+  "description": "Talk \nIn 2016 I wrote a blog post called Fizz Buzz in Tensorflow, which went modestly viral. In the years since I have invented and/or collected other stupid and/or clever ways of solving Fizz Buzz, the ten most interesting of which I expounded on in \u201cTen Essays on Fizz Buzz.\u201d In this talk I\u2019ll quickly take you through these ten Python solutions, most of which are delightfully surprising.\n\nSpeaker\nJoel Grus is Principal Engineer at Capital Group, where he leads a small team focused on the design and development of machine learning and data products. He\u2019s the author of the quirky \u201cTen Essays on Fizz Buzz\u201d, the beloved \u201cData Science from Scratch\u201d, and the polarizing JupyterCon presentation \u201cI Don\u2019t Like Notebooks.\u201d\n\n\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. \n\n00:00 Welcome!\n00:10 Fizz Buzz overview\n1:55 - 100 print statements\n2:16 - if/elif/elif/else\n2:34 - the cycle of 15\n2:58 - Euclid's Solution\n3:28 - Trigonometry\n3:56 - A big number\n4:21 - Infinite Iterables\n4:51 - Random Guessing\n5:29 - Matrix Multiplication\n5:55 - Fizz Buzz in Tensorflow\n\nS/o to https://github.com/stobinaator for the video timestamps!\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 500,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    },
+    {
+      "label": "https://github.com/stobinaator",
+      "url": "https://github.com/stobinaator"
+    }
+  ],
+  "speakers": [
+    "Joel Grus"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/E7JAIF9FOnM/maxresdefault.webp",
+  "title": "Ten Ways To Fizz Buzz",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=E7JAIF9FOnM"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/joris-van-den-bossche-whats-new-in-pandas-pydata-global-2020.json b/pydata-global-2020/videos/joris-van-den-bossche-whats-new-in-pandas-pydata-global-2020.json
new file mode 100644
index 000000000..d58da1c47
--- /dev/null
+++ b/pydata-global-2020/videos/joris-van-den-bossche-whats-new-in-pandas-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nPandas finally reached a 1.0 release in early 2020. But, there is still a lot of development activity going on. This talk will give an overview of what\u2019s happening in the latest releases of pandas and where we are heading to, and highlight some important milestones for the project achieved over the last year.\n\nSpeakers\nJoris is a core contributor to Pandas and Apache Arrow and maintainer of GeoPandas. I did a PhD at Ghent University and VITO in air quality research, worked at the Paris-Saclay Center for Data Science, and currently, I am a freelance software developer and teacher and working for Ursa Labs.\n\nTom is a software engineer at Anaconda where he works on open-source libraries like pandas and Dask.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1963,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Joris Van den Bossche"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/YAhjagucQBs/maxresdefault.webp",
+  "title": "Whats New In Pandas",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=YAhjagucQBs"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/jose-berengueres-data-visualization-storytelling-pydata-global-2020.json b/pydata-global-2020/videos/jose-berengueres-data-visualization-storytelling-pydata-global-2020.json
new file mode 100644
index 000000000..fffed2689
--- /dev/null
+++ b/pydata-global-2020/videos/jose-berengueres-data-visualization-storytelling-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nIn this interdisciplinary (Art + Design) talk we explore the reasons behind the epidemic of poor visuals; how to avoid death by Tableau, how better visualizing can help you communicate your data better and how to avoid sexism and other biases in your charts.\n\nSpeaker\nJose Berengueres studied in Barcelona and Tokyo. He is PhD in robotics from TokyoTech. Since 2011 he is with the UAE University where he has authored several books on design thinking and data visualization. An avid sailor and former entrepreneur, he combines his love for teaching with mentoring and consulting on data science, UX and design thinking. He is also a Kaggle master and angel investor in the #Edtech citationSy.com .\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 665,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Jose Berengueres"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/plFPTDwk66s/maxresdefault.webp",
+  "title": "Data Visualization & Storytelling",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=plFPTDwk66s"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/juan-de-dios-santos-is-neural-network-better-than-ash-at-detecting-team-rocket-pydata-global-2020.json b/pydata-global-2020/videos/juan-de-dios-santos-is-neural-network-better-than-ash-at-detecting-team-rocket-pydata-global-2020.json
new file mode 100644
index 000000000..89157ae27
--- /dev/null
+++ b/pydata-global-2020/videos/juan-de-dios-santos-is-neural-network-better-than-ash-at-detecting-team-rocket-pydata-global-2020.json
@@ -0,0 +1,32 @@
+{
+  "description": "Talk \nIn the world of Pokemon, there is a running gag in the inability of protagonist Ash Ketchum, at recognizing the series antagonist, Team Rocket. This fact got me thinking: is a neural network better than Ash? To answer this, I\u2019m using TensorFlow, TensorFlow.js, and Google AutoML to visualize a network\u2019s activation maps to interpret why it says this is Team Rocket.\n\nSpeaker \nJuan is a Data Engineer at LOVOO, a dating, and social platform. As part of the LVPD team, he\u2019s responsible for developing methods to detect and combat the fraudsters and spammers encountered in the platform.\n\nIn his free time\u2014when he\u2019s not dealing with fraud\u2014you will surely find him experimenting with personal data to learn curious details about himself or having fun with object detection models. You can find more about his work at https://juandes.com.\n\nJuan holds a BSc in Computer Science from the University of Puerto Rico - Rio Piedras Campus and an MSc in Computer Science from Uppsala University in Sweden.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1674,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    },
+    {
+      "label": "https://juandes.com.",
+      "url": "https://juandes.com."
+    }
+  ],
+  "speakers": [
+    "Juan De Dios Santos"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/xLPriI2X_NM/maxresdefault.webp",
+  "title": "Is Neural Network Better Than Ash at Detecting Team Rocket",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=xLPriI2X_NM"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/justin-nguyen-building-a-successful-data-science-team-pydata-global-2020.json b/pydata-global-2020/videos/justin-nguyen-building-a-successful-data-science-team-pydata-global-2020.json
new file mode 100644
index 000000000..b388fddf8
--- /dev/null
+++ b/pydata-global-2020/videos/justin-nguyen-building-a-successful-data-science-team-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk\nCreating and growing an elite data science team is no small feat. In this talk, we will discuss the three key areas to focus on when setting up your data science organization: building the right team, selecting the right use cases, and rapid technical enablement. While the path forward may seem daunting, this flexible yet focused approach will position you for success.\n\nSpeaker \nAs a trusted leader and practitioner in Data Science and AI, Justin partners with clients to deliver robust data-driven solutions that increase revenue, reduce costs, and lead to greater operational efficiencies. Justin has completed undergraduate and graduate studies in engineering and computer science at Georgia Tech and Stanford University, and he has more than eight years of experience supporting clients in industries including energy, hospitality, and software development. He has built and commercialized AI products using NLP as well as guided large enterprises through their AI journey and transformation.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1524,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Justin Nguyen"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/Jfi7o3lTQNg/maxresdefault.webp",
+  "title": "Building A Successful Data Science Team",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=Jfi7o3lTQNg"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/liucija-latanauskaite-why-i-didn-t-use-deep-learning-for-my-image-recognition-pydata-global-2020.json b/pydata-global-2020/videos/liucija-latanauskaite-why-i-didn-t-use-deep-learning-for-my-image-recognition-pydata-global-2020.json
new file mode 100644
index 000000000..3af4b0e8d
--- /dev/null
+++ b/pydata-global-2020/videos/liucija-latanauskaite-why-i-didn-t-use-deep-learning-for-my-image-recognition-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nThis is a how-things-went-wrong story of using deep learning to match images of climbing holds in gyms. But there\u2019s a happy ending: a more traditional computer vision solution outperforms neural nets.\nSpeaker \nI am data scientist coming from a statistical background, always on the lookout for problems to solve using data.\n\nBy day, I work at GoCardless, a recurring payments provider, where I create machine learning products to reduce payment failure rates and tackle fraud.\n\nMy second life is rock climbing and working on Climbicus - an app for logging climbing routes at an indoor gym, leveraging computer vision techniques.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1668,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Liucija Latanauskaite"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/1e0K7Mjf3MM/maxresdefault.webp",
+  "title": "Why I didn't use deep learning for my image recognition",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=1e0K7Mjf3MM"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/luis-lopez-climate-change-analyzing-remote-sensing-data-with-python-pydata-global-2020.json b/pydata-global-2020/videos/luis-lopez-climate-change-analyzing-remote-sensing-data-with-python-pydata-global-2020.json
new file mode 100644
index 000000000..9310f81e2
--- /dev/null
+++ b/pydata-global-2020/videos/luis-lopez-climate-change-analyzing-remote-sensing-data-with-python-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nAt The National Snow and Ice Data Center in Boulder, Colorado we distribute a trove of remote sensing data that is used globally to conduct important scientific research. We\u2019ll explore in an interactive way some of these data sets scientists use to assess and forecast climate change.\n\nSpeaker \nI\u2019m a Software Engineer at the National Snow and Ice Data Center. NSIDC is one of 9 data centers for NASA\u2019s Earth Data systems. I\u2019m currently working on building services on top of remote sensing data and trying to close the gap between cryospheric research and understandable, reproducible science.\n\nI\u2019m from Mexico and attended grad school at the University of Colorado.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 2116,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Luis Lopez"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/lJKxIjZqu7s/maxresdefault.webp",
+  "title": "Climate change analyzing remote sensing data with Python",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=lJKxIjZqu7s"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/martin-durant-asynchronous-fsspec-file-operations-pydata-global-2020.json b/pydata-global-2020/videos/martin-durant-asynchronous-fsspec-file-operations-pydata-global-2020.json
new file mode 100644
index 000000000..89c0e5857
--- /dev/null
+++ b/pydata-global-2020/videos/martin-durant-asynchronous-fsspec-file-operations-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk\nAsyncio compatibility has been added recently to some fsspec-based file system implementations: http, s3 and gcs. Not only can you now call (some of) the API from async/await-style code, but bulk operations can be carried out massively concurrently, with potentially great speed-ups for file upload/download, copy and delete.\n\nSpeaker\nA former astrophysicist, Martin has worked in multiple academic positions, including medical imaging research. After this, Martin became a data scientist, and has since been working for Anaconda for five years. In open source, he is a member of the Dask, Intake, Streamz and Zarr maintenance teams, with specialisms in data access, remote filesystems and data formats.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 451,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Martin Durant"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/7XDBM3pW2ls/maxresdefault.webp",
+  "title": "Asynchronous fsspec file operations",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=7XDBM3pW2ls"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/massimiliano-ungheretti-modelling-the-extreme-using-quantile-regression-pydata-global-2020.json b/pydata-global-2020/videos/massimiliano-ungheretti-modelling-the-extreme-using-quantile-regression-pydata-global-2020.json
new file mode 100644
index 000000000..3fea038c2
--- /dev/null
+++ b/pydata-global-2020/videos/massimiliano-ungheretti-modelling-the-extreme-using-quantile-regression-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nGiven a student\u2019s grades, what would be a good score in their exam? An econometrician could model the conditional quantiles directly. We\u2019ll show their linear models and how you can implement neural net versions in tensorflow or use xgboost. Even if you never end up fitting a quantile regression, you\u2019ll learn a new metric for evaluating how well you are estimating extreme examples!\n\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1608,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Massimiliano Ungheretti"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/GpRuhE04lLs/maxresdefault.webp",
+  "title": "Modelling the extreme using Quantile Regression",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=GpRuhE04lLs"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/nicole-carlson-michael-sugimura-building-one-multitask-model-to-rule-them-all-pydata-global-2020.json b/pydata-global-2020/videos/nicole-carlson-michael-sugimura-building-one-multitask-model-to-rule-them-all-pydata-global-2020.json
new file mode 100644
index 000000000..098f09856
--- /dev/null
+++ b/pydata-global-2020/videos/nicole-carlson-michael-sugimura-building-one-multitask-model-to-rule-them-all-pydata-global-2020.json
@@ -0,0 +1,29 @@
+{
+  "description": "Talk \nThis is the story of how we built the Octopod library. Octopod streamlines the training of multi-task PyTorch networks. It supports training with multiple task-specific datasets, multiple inputs, and ensembles of multi-task networks. We will discuss technical details of the library as well as interpersonal challenges we faced along the way.\n\nSpeakers\nNicole is a Data Science Manager at ShopRunner. She\u2019s passionate about diverse and inclusive teams.\n\nMichael is a Senior Data Scientist at ShopRunner. He is a data scientist, gamer, martial artist, photographer, and chef\u2026 also part time house cat. \n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1652,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Nicole Carlson",
+    "Michael Sugimura"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/koYLHZ_GvrM/maxresdefault.webp",
+  "title": "Building one multitask model to rule them all",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=koYLHZ_GvrM"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/shashank-shekhar-using-dominance-analysis-for-accurate-feature-importance-pydata-global-2020.json b/pydata-global-2020/videos/shashank-shekhar-using-dominance-analysis-for-accurate-feature-importance-pydata-global-2020.json
new file mode 100644
index 000000000..a9d57d30d
--- /dev/null
+++ b/pydata-global-2020/videos/shashank-shekhar-using-dominance-analysis-for-accurate-feature-importance-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nI will demonstrate the usage of Azen and Budescu\u2019s Dominance Analysis (leveraging the Python library developed by us) to accurately determine the relative importance of features in scenarios where there is need to marginally allocate resources to enable an outcome.\n\nSpeaker\nShashank is Data Sciences leader with diverse experience across verticals including CPG, Retail, Hitech and E-commerce domains. He is currently heading the Aritficial Intelligence Labs at Subex. In the past, he has worked in VMware, Amazon, Flipkart and Target and has been involved in solving various complex business problems using Machine Learning and Deep Learning. He has been part of the program committee of several international conferences like ICDM and MLDM and was selected as a mentor in Global Datathon 2018 organized by Data Sciences Society. He has multiple publications in the field of data sciences, machine learning, deep learning and image recognition in several international journals of repute to his credit. He has spoken at many summits and conferences like Big Data Lake Summit, PlugIn etc. He has also published two open source libraries on Python and is an active contributor to the global Python community.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 603,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Shashank Shekhar"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/IuX5godOggs/maxresdefault.webp",
+  "title": "Using Dominance Analysis for accurate feature importance",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=IuX5godOggs"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/simona-maggio-learning-from-your-model-s-mistakes-pydata-global-2020.json b/pydata-global-2020/videos/simona-maggio-learning-from-your-model-s-mistakes-pydata-global-2020.json
new file mode 100644
index 000000000..14ae60706
--- /dev/null
+++ b/pydata-global-2020/videos/simona-maggio-learning-from-your-model-s-mistakes-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nUnderstanding in what situations an ML model fails is essential to attempt to fix the model\u2019s flaws. For data scientists concerned with robust ML system design, this talk will show how to streamline error analysis thanks to Model Performance Predictors, by automatically breaking down model failures into meaningful clusters and comparing them with the successfully predicted baseline.\n\nSpeaker \nAfter obtaining a PhD in Biomedical Image Processing in 2011, Simona Maggio worked in several companies (CEA, Thales, Rakuten) as a Research Engineer in Computer Vision and Natural Language Processing for applications ranging from video surveillance to document digitization and e-commerce. She\u2019s now Senior Research Scientist at Dataiku, exploring MLOps topics, such as model debugging, robustness and interpretability.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 637,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Simona Maggio"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/zTcEoYwYTVI/maxresdefault.webp",
+  "title": "Learning from your (model's) mistakes",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=zTcEoYwYTVI"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/sonam-pankaj-timeseries-forecasting-with-ml-algorithms-and-there-comparisons-pydata-global-2020.json b/pydata-global-2020/videos/sonam-pankaj-timeseries-forecasting-with-ml-algorithms-and-there-comparisons-pydata-global-2020.json
new file mode 100644
index 000000000..c625dadc0
--- /dev/null
+++ b/pydata-global-2020/videos/sonam-pankaj-timeseries-forecasting-with-ml-algorithms-and-there-comparisons-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nTimeSeries Forecasting using differenct tool non-ML and ML, different algorithms like moving average, SVM(support vector machine), LSTM,( Long-Short Term Memory) and Prophet. We will also compare the accuracy using RMSE. Dataset has been taken from Covid19 kaggle. Since we have seen what a huge impact coronavirus had on our daily lives, also we will understand about exponential growth.\n\nSpeaker \nSpeaker is very passionate about data science and machine learning. She has been working in this field since past 3 years and have worked on understanding mathematics behind Machine Learning algorithms.\n\nShe is also a tech speaker, she has delivered talks on the Machine learning and Data Science at PyCon India 2019 and PyData BBSR 2020 PyCon India: \u201cSolving Industrial Problems with Machine Learning\u201d in which she presented how she used SVM for detecting corrosion in pipeline images. PyData BBSR : \u201cSupervised and Unsupervised Machine Learning Algorithms\u201d In which she presented various Algorithms of both and their applications.\n\nShe has worked on level 4 autonomous vehicle and was also appointed as an Adjunct Professor for robotics and computer vision. Currently she is working in an IIT Madras incubated company as Lead Software Engineer. She is an unique blender of technology with entrepreneurship and she looks forward for PyData Global.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1518,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Sonam Pankaj"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/BxN2RcTwv7M/maxresdefault.webp",
+  "title": "TimeSeries Forecasting with ML Algorithms and their comparisons",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=BxN2RcTwv7M"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/stuart-lynn-using-eolearn-to-build-a-machine-learning-pipeline-pydata-global-2020.json b/pydata-global-2020/videos/stuart-lynn-using-eolearn-to-build-a-machine-learning-pipeline-pydata-global-2020.json
new file mode 100644
index 000000000..beca82a39
--- /dev/null
+++ b/pydata-global-2020/videos/stuart-lynn-using-eolearn-to-build-a-machine-learning-pipeline-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nThe past 10 years has seen an explosion of data from remote sensing satellites.This data, which can be used for a wide range of applications, can be hard to obtain and use. EOLearn aims to bridge the gap between the remote sensing and machine learning world. In this talk, we will discuss how to build a ML remote sensing pipeline in python using an ocean plastic detection project as an example.\n\nSpeaker\nStuart Lynn is the data science lead at the Data Clinic where he helps nonprofits use data to better serve their communities, conducts independent research and develops new tooling that enhances the use of open data.\n\nStuart is a firm believer that access to good data and tools can be a game-changer, having previously spent 6 years working at the Zooniverse, the world\u2019s largest collection of online citizen science projects, and also headed up data science at CARTO, a company that specializes in making spatial data and analysis accessible.\n\nStuart holds a PhD in Astrophysics and a Masters in Mathematical Physics from the University of Edinburgh. When not working at Data Clinic you can find Stuart buried in his side projects, including building tools to explore historic maps, creative coding and tinkering with hardware.\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1970,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Stuart Lynn"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/SVsOa1_RpCw/maxresdefault.webp",
+  "title": "Using EOLearn to build a machine learning pipeline",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=SVsOa1_RpCw"
+    }
+  ]
+}
diff --git a/pydata-global-2020/videos/thomas-caswell-seperation-of-scales-pydata-global-2020.json b/pydata-global-2020/videos/thomas-caswell-seperation-of-scales-pydata-global-2020.json
new file mode 100644
index 000000000..c4865a2bb
--- /dev/null
+++ b/pydata-global-2020/videos/thomas-caswell-seperation-of-scales-pydata-global-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Talk \nAs programmers we work in deeply layered systems. When a layer below us \u201cjust works\u201d things feel easy and life is great! However, all to often it feels like our tools fight back and get in the way. In this talk, we will discuss how to identify the good scales and abstractions in software, and how to build pleasant tools for ourselves and others.\n\nSpeaker\nThomas is a soft-matter physicist who now developer software for scientists. He develops data acquisition, management, and analysis tools at NSLS-II at BNL, as a core maintainer of h5py, and is the current Project Lead of Matplotlib.\n\n\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 2105,
+  "language": "eng",
+  "recorded": "2020-11-11",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydataglobal.github.io/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Thomas Caswell"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/P85UIuMovnI/maxresdefault.webp",
+  "title": "Separation Of Scales",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=P85UIuMovnI"
+    }
+  ]
+}