scikit-learn-06-data-science-pipeline.json

{
  "copyright_text": "Standard YouTube License",
  "description": "In this video, we'll cover the data science pipeline from data ingestion (with pandas) to data visualization (with seaborn) to machine learning (with scikit-learn). We'll learn how to train and interpret a linear regression model, and then compare three possible evaluation metrics for regression problems. Finally, we'll apply the train/test split procedure to decide which features to include in our model.\n\nThis is the sixth video in the series, `Introduction to machine learning with scikit-learn <http://www.dataschool.io/machine-learning-with-scikit-learn/>`__. The notebook and resources shown in the video are available on `GitHub <https://github.com/justmarkham/scikit-learn-videos>`__.",
  "duration": 2069,
  "language": "eng",
  "recorded": "2015-05-28",
  "related_urls": [
    "http://www.dataschool.io/machine-learning-with-scikit-learn/",
    "https://github.com/justmarkham/scikit-learn-videos"
  ],
  "slug": "scikit-learn-06-data-science-pipeline",
  "speakers": [
    "Kevin Markham"
  ],
  "tags": [
    "machine learning",
    "data science",
    "scikit-learn",
    "tutorial",
    "Data School",
    "pandas",
    "seaborn",
    "linear regression",
    "model evaluation",
    "feature selection",
    "visualization"
  ],
  "thumbnail_url": "https://i1.ytimg.com/vi/3ZWuPVWq7p4/maxresdefault.jpg",
  "title": "Data science in Python: pandas, seaborn, scikit-learn",
  "videos": [
    {
      "type": "youtube",
      "url": "https://www.youtube.com/watch?v=3ZWuPVWq7p4"
    }
  ]
}