{"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":"markdown","source":"","metadata":{},"attachments":{"45296506-9933-4e99-9e00-909af4172c15.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"# MLB Player Digital Engagement Forecasting\n\n## Problem Statement\n\nIn this competition, we need to `predict how fans engage with MLB players’ digital content on a daily basis for a future date range`. We’ll have access to player performance data, social media data, and team factors like market size. Successful models will provide new insights into what signals most strongly correlate with and influence engagement. We are tasked with `forecasting four different measures of engagement (target1 - target4)` for a subset of MLB players who are active in the 2021 season.","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2021-06-17T02:56:52.615257Z","iopub.execute_input":"2021-06-17T02:56:52.615653Z","iopub.status.idle":"2021-06-17T02:56:54.467413Z","shell.execute_reply.started":"2021-06-17T02:56:52.615569Z","shell.execute_reply":"2021-06-17T02:56:54.466295Z"}}},{"cell_type":"markdown","source":"
","metadata":{"execution":{"iopub.status.busy":"2021-06-18T17:45:17.817486Z","iopub.execute_input":"2021-06-18T17:45:17.817913Z","iopub.status.idle":"2021-06-18T17:45:17.828565Z","shell.execute_reply.started":"2021-06-18T17:45:17.817835Z","shell.execute_reply":"2021-06-18T17:45:17.827265Z"}}},{"cell_type":"markdown","source":"## Data Understanding\n\n* `players.csv` - Library containing high level information about all MLB players.\n* `teams.csv` - Library containing high level information about all MLB teams.\n* `seasons.csv` - Information about start and end dates of all seasons in this dataset.\n* `awards.csv` - A collection of awards given out prior to 01/01/2018 (the first date in train.csv).\n* `train.csv` - the training set.\n* `example_test.csv` - an example in the form of the test set that we'll be evaluated on.\n* `example_sample_submission.csv` - A sample submission file in the correct format based on the example test set.","metadata":{}},{"cell_type":"markdown","source":"
","metadata":{"execution":{"iopub.status.busy":"2021-06-18T17:46:06.841378Z","iopub.execute_input":"2021-06-18T17:46:06.841756Z","iopub.status.idle":"2021-06-18T17:46:06.84742Z","shell.execute_reply.started":"2021-06-18T17:46:06.841719Z","shell.execute_reply":"2021-06-18T17:46:06.846096Z"}}},{"cell_type":"markdown","source":"## Exploratory Data Analysis using Pandas Profiling\n\n\nThe aim of this notebook is to show how we can use Pandas Profiling for Exploratory Data Analysis of a dataset.
\nThis can be very useful for analyzing the data quickly and getting helful insights.
\n
\n\n`We're going to see different ways of using Pandas Profiling through Classes and Functions.`\n\n* [Classes](#section-one)\n* [Functions](#section-two)\n* [Condensed Code](#section-three)","metadata":{}},{"cell_type":"markdown","source":"
","metadata":{}},{"cell_type":"markdown","source":"## Pandas Profiling\n\n`Pandas Profiling` can be used to generate reports from a pandas `DataFrame`.\n\n`df.describe()` function in pandas provides some basic data analysis whereas `pandas_profiling` extends the pandas DataFrame with `df.profile_report()` for quick and better data analysis\n\nFor each column the following statistics are presented in an interactive HTML report:\n\n* `Type inference` - detect the types of columns in a dataframe.\n* `Essentials` - type, unique values, missing values\n* `Quantile statistics` like minimum value, Q1, median, Q3, maximum, range, interquartile range\n* `Descriptive statistics` like mean, mode, standard deviation, sum, median absolute deviation, coefficient of variation, kurtosis, skewness\n* `Most frequent values`\n* `Histogram`\n* `Correlations` highlighting of highly correlated variables, Spearman, Pearson and Kendall matrices\n* `Missing values` matrix, count, heatmap and dendrogram of missing values\n* `Text analysis` learn about categories (Uppercase, Space), scripts (Latin, Cyrillic) and blocks (ASCII) of text data.\n* `File and Image analysis` extract file sizes, creation dates and dimensions and scan for truncated images or those containing EXIF information.\n\nYou can check out the URL for more information: https://github.com/pandas-profiling/pandas-profiling","metadata":{}},{"cell_type":"markdown","source":"
","metadata":{}},{"cell_type":"markdown","source":"### Importing the required libraries","metadata":{}},{"cell_type":"code","source":"# Data manipulation and analysis\nimport pandas as pd\n# Exploratory Data Analysis\nimport pandas_profiling\n# To generate reports from a Dataset stored as a pandas DataFrame.\nfrom pandas_profiling import ProfileReport","metadata":{"execution":{"iopub.status.busy":"2021-06-18T18:19:41.381122Z","iopub.execute_input":"2021-06-18T18:19:41.381679Z","iopub.status.idle":"2021-06-18T18:19:41.385572Z","shell.execute_reply.started":"2021-06-18T18:19:41.381646Z","shell.execute_reply":"2021-06-18T18:19:41.384675Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Defining variables for storing the dataset names and their path","metadata":{"_kg_hide-output":true}},{"cell_type":"code","source":"INPUT_PATH = '../input/mlb-player-digital-engagement-forecasting'\nOUTPUT_PATH = '.'\nPLAYERS = 'players'\nTEAMS = 'teams'\nAWARDS = 'awards'\nSEASONS = 'seasons'","metadata":{"execution":{"iopub.status.busy":"2021-06-18T18:19:43.082685Z","iopub.execute_input":"2021-06-18T18:19:43.083057Z","iopub.status.idle":"2021-06-18T18:19:43.087304Z","shell.execute_reply.started":"2021-06-18T18:19:43.083025Z","shell.execute_reply":"2021-06-18T18:19:43.086265Z"},"_kg_hide-output":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n# Class for Exploratory Data Analysis using Pandas Profiling","metadata":{}},{"cell_type":"code","source":"class PandasProfile:\n def __init__(self, file_name):\n self.file_name = file_name\n self.input_file = INPUT_PATH + '/' + file_name + '.csv';\n self.output_file = OUTPUT_PATH + '/' + file_name + '.html';\n \n def import_file(self, max_sample = None):\n if(max_sample is not None):\n df = pd.read_csv(self.input_file, nrows = max_sample)\n else:\n df = pd.read_csv(self.input_file)\n return df\n\n def create_pandas_profile(self, dataframe):\n profile = ProfileReport(dataframe, title='Data Analysis Report for {}'.format(self.file_name), html={'style':{'full_width':True}})\n return profile\n \n def display_data_profile(self, pandas_profile):\n pandas_profile.to_notebook_iframe()\n \n def export_data_profile(self, pandas_profile):\n pandas_profile.to_file(output_file = self.output_file)\n \n def complete_profile(self, max_sample = None):\n df = self.import_file(max_sample)\n pandas_profile = self.create_pandas_profile(df)\n self.export_data_profile(pandas_profile)\n self.display_data_profile(pandas_profile)","metadata":{"execution":{"iopub.status.busy":"2021-06-18T18:39:41.094173Z","iopub.execute_input":"2021-06-18T18:39:41.094561Z","iopub.status.idle":"2021-06-18T18:39:41.104237Z","shell.execute_reply.started":"2021-06-18T18:39:41.094524Z","shell.execute_reply":"2021-06-18T18:39:41.103299Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Creating the data reports using the user-defined Class `PandasProfile`","metadata":{}},{"cell_type":"code","source":"players_profile = PandasProfile(PLAYERS)\nplayers_profile.complete_profile()","metadata":{"execution":{"iopub.status.busy":"2021-06-18T18:22:00.429181Z","iopub.execute_input":"2021-06-18T18:22:00.429523Z","iopub.status.idle":"2021-06-18T18:22:10.906046Z","shell.execute_reply.started":"2021-06-18T18:22:00.429494Z","shell.execute_reply":"2021-06-18T18:22:10.905234Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Similarly profile can be created for Seasons, Teams and Awards using:\n* `seasons_profile = PandasProfile(SEASONS)`
\n* `teams_profile = PandasProfile(TEAMS)`","metadata":{}},{"cell_type":"markdown","source":"
","metadata":{}},{"cell_type":"markdown","source":"\n# Modular functions for EDA using Pandas Profiling","metadata":{}},{"cell_type":"markdown","source":"### Reads the dataset from the csv file and returns it","metadata":{}},{"cell_type":"code","source":"def import_file(file_path, max_sample = None):\n if(max_sample is not None):\n df = pd.read_csv(file_path, nrows = max_sample)\n else:\n df = pd.read_csv(file_path)\n return df","metadata":{"execution":{"iopub.status.busy":"2021-06-18T18:46:09.218022Z","iopub.execute_input":"2021-06-18T18:46:09.218492Z","iopub.status.idle":"2021-06-18T18:46:09.223481Z","shell.execute_reply.started":"2021-06-18T18:46:09.218462Z","shell.execute_reply":"2021-06-18T18:46:09.222759Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Created the pandas profile from the dataframe","metadata":{}},{"cell_type":"code","source":"def create_pandas_profile(dataframe):\n profile = ProfileReport(dataframe, title='Data Analysis Report', html={'style':{'full_width':True}})\n return profile","metadata":{"execution":{"iopub.status.busy":"2021-06-18T18:31:30.622186Z","iopub.execute_input":"2021-06-18T18:31:30.622568Z","iopub.status.idle":"2021-06-18T18:31:30.627223Z","shell.execute_reply.started":"2021-06-18T18:31:30.622532Z","shell.execute_reply":"2021-06-18T18:31:30.62616Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Displays the data analysis report in the notebook","metadata":{}},{"cell_type":"code","source":"def display_data_profile(pandas_profile):\n pandas_profile.to_notebook_iframe()","metadata":{"execution":{"iopub.status.busy":"2021-06-18T18:31:30.757497Z","iopub.execute_input":"2021-06-18T18:31:30.758067Z","iopub.status.idle":"2021-06-18T18:31:30.762485Z","shell.execute_reply.started":"2021-06-18T18:31:30.758017Z","shell.execute_reply":"2021-06-18T18:31:30.761656Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Exports the data analysis report as an interactive html","metadata":{}},{"cell_type":"code","source":"def export_data_profile(pandas_profile, export_path = './Report.html'):\n pandas_profile.to_file(output_file = export_path)","metadata":{"execution":{"iopub.status.busy":"2021-06-18T18:31:32.25028Z","iopub.execute_input":"2021-06-18T18:31:32.250668Z","iopub.status.idle":"2021-06-18T18:31:32.254934Z","shell.execute_reply.started":"2021-06-18T18:31:32.250622Z","shell.execute_reply":"2021-06-18T18:31:32.253766Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Complete profiling to handle everything in one function :\n* Reads the data from csv files\n* Creates pandas profile from the dataframe\n* Exports the data analysis report as an interactive html\n* Displays the data analysis report in the notebook","metadata":{}},{"cell_type":"code","source":"def complete_profile(data_file_path, html_export_path = './Report.html') :\n file_path = data_file_path\n df = import_file(file_path)\n pandas_profile = create_pandas_profile(df)\n export_data_profile(pandas_profile, export_path = html_export_path)\n display_data_profile(pandas_profile)","metadata":{"execution":{"iopub.status.busy":"2021-06-18T18:31:32.397474Z","iopub.execute_input":"2021-06-18T18:31:32.397892Z","iopub.status.idle":"2021-06-18T18:31:32.402903Z","shell.execute_reply.started":"2021-06-18T18:31:32.397849Z","shell.execute_reply":"2021-06-18T18:31:32.401781Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Creating the data reports using the user-defined functions","metadata":{}},{"cell_type":"code","source":"complete_profile('../input/mlb-player-digital-engagement-forecasting/teams.csv', 'Teams.html')","metadata":{"execution":{"iopub.status.busy":"2021-06-18T18:33:04.121393Z","iopub.execute_input":"2021-06-18T18:33:04.121787Z","iopub.status.idle":"2021-06-18T18:33:04.125722Z","shell.execute_reply.started":"2021-06-18T18:33:04.121757Z","shell.execute_reply":"2021-06-18T18:33:04.124712Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Similarly we can use it to create EDA reports for other datasets as well:\n* `complete_profile('../input/mlb-player-digital-engagement-forecasting/players.csv', 'Players.html')`\n* `complete_profile('../input/mlb-player-digital-engagement-forecasting/seasons.csv', 'Seasons.html')`","metadata":{}},{"cell_type":"markdown","source":"
","metadata":{}},{"cell_type":"markdown","source":"\n# Condensed code for EDA using Pandas Profile","metadata":{}},{"cell_type":"code","source":"# Read the data from csv file\ndataframe = pd.read_csv('../input/mlb-player-digital-engagement-forecasting/seasons.csv')\n# Creates a pandas data profile\npandas_profile = ProfileReport(dataframe, title='Data Analysis Report for Seasons', html={'style':{'full_width':True}})\n# Export the data analysis report to an interactive HTML\npandas_profile.to_file(output_file = 'Seasons.html')\n# Displays the data analysis report in the notebook\npandas_profile.to_notebook_iframe()","metadata":{"execution":{"iopub.status.busy":"2021-06-18T19:07:10.567194Z","iopub.execute_input":"2021-06-18T19:07:10.570839Z","iopub.status.idle":"2021-06-18T19:07:24.175322Z","shell.execute_reply.started":"2021-06-18T19:07:10.570673Z","shell.execute_reply":"2021-06-18T19:07:24.174256Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"
","metadata":{}},{"cell_type":"markdown","source":"### Creating data analysis report for Awards using user-defined `PandasProfile` Class","metadata":{}},{"cell_type":"code","source":"awards_profile = PandasProfile(AWARDS)\nawards_profile.complete_profile()","metadata":{},"execution_count":null,"outputs":[]}]}