{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"raw","source":"# Basic EDA using [DataPrep](https://pypi.org/project/dataprep/)\nData Prep is an awesome library by the SFU Data Science Research Group to automate and speedup the EDA process. <br>\nwe can create awesome detailed reports on our dataset with litrally a sinlge line of code \nIt comes with its own datasets too.<br>\nIn this notebook I have used the library to create reports on the datasets provided to us for the competion.","metadata":{}},{"cell_type":"markdown","source":"# Installs and Imports","metadata":{}},{"cell_type":"code","source":"import gc\nfrom pathlib import Path\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport os\nimport random\n\nimport plotly.graph_objects as go\nimport seaborn as sns\n\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Aim\npredict how fans engage with MLB players’ digital content on a daily basis for a future date range.\nprovide new insights into what signals most strongly correlate with and influence engagement.\n","metadata":{}},{"cell_type":"markdown","source":"# Data\n- player performance data\n- social media data\n team factors like market size.","metadata":{}},{"cell_type":"code","source":"\ntrain = pd.read_csv('../input/mlb-player-digital-engagement-forecasting/train.csv')\nawards = pd.read_csv('../input/mlb-player-digital-engagement-forecasting/awards.csv')\nplayers = pd.read_csv('../input/mlb-player-digital-engagement-forecasting/players.csv')\nseasons = pd.read_csv('../input/mlb-player-digital-engagement-forecasting/seasons.csv')\nteams = pd.read_csv('../input/mlb-player-digital-engagement-forecasting/teams.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Train","metadata":{}},{"cell_type":"code","source":"train.head()\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Awards","metadata":{}},{"cell_type":"markdown","source":"## Teams","metadata":{}},{"cell_type":"markdown","source":"## Players","metadata":{}},{"cell_type":"markdown","source":"## Seasons","metadata":{}}]}