Add script for Zadanie1

README.md

@@ -0,0 +1,3 @@
+Inżynieria Uczenia Maszynowego
+Dataset: https://www.kaggle.com/eugenioscionti/scraping-rotten-tomatoes-to-enrich-netflix-dataset
+ium_zadanie1.py - python script for Zadanie 1

ium_zadanie1.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python3.7
+
+
+import pandas as pd
+import seaborn as sns
+import datetime
+import matplotlib.pyplot as plt
+
+netflix=pd.read_csv('netflix_titles_enriched.csv')
+
+netflix_cleaned = netflix[netflix.rottentomatoes_audience_score > 0].sort_values(by = 'rottentomatoes_audience_score')
+netflix_cleaned.rottentomatoes_audience_score /= 100
+netflix_cleaned.drop(['rottentomatoes_audience_#reviews',
+       'rottentomatoes_audience_review', 'rottentomatoes_tomatometer_score',
+       'rottentomatoes_critics_#reviews', 'rottentomatoes_critic_review'], axis = 1)
+
+netflix_cleaned.date_added = netflix_cleaned.date_added.dropna().apply(lambda x: datetime.datetime.strptime(x[1:] if x[0] == ' ' else x, '%B %d, %Y'))
+
+netflix_cleaned.update(netflix_cleaned.select_dtypes(include = 'object').apply(lambda col: col.str.lower()))
+
+
+movies = netflix_cleaned[netflix_cleaned.type == 'movie']
+series = netflix_cleaned[netflix_cleaned.type == 'tv show']
+
+
+movies.duration = movies.duration.str.extract(r'(\d*)( min)')[0].astype('int32')
+
+from sklearn.preprocessing import MultiLabelBinarizer
+mlb = MultiLabelBinarizer()
+
+movies = movies.join(pd.DataFrame(mlb.fit_transform(movies.pop('listed_in').str.split(', ')),
+                          columns=mlb.classes_,
+                          index=movies.index))
+movies.drop(['movies'], axis = 1)
+
+import sklearn
+from sklearn.model_selection import train_test_split
+movies_train, movies_test = sklearn.model_selection.train_test_split(movies,test_size=0.20, random_state=42)
+movies_test, movies_val = sklearn.model_selection.train_test_split(movies_test,test_size=0.50, random_state=42)
+
+movies_subsets = [movies_train, movies_test, movies_val]
+for subset in movies_subsets:
+    print(subset.shape[0])
+    print(subset.describe(include='all'))
+
+movies_subsets = pd.concat(movies_subsets, keys = ['Train','Test','Validation'])
+movies_subsets = movies_subsets.reset_index()
+ax = sns.boxplot(data = movies_subsets, x = 'level_0', y = 'rottentomatoes_audience_score')
+ax.set(title = 'Audience score distribution between subsets', ylabel = 'Audience score on Rotten Tomatoes', xlabel = 'SUBSET')
+plt.show(ax)
+
+
+series.duration = series.duration.str.extract(r'(\d*)( seasons?)')[0].astype('int32')
+
+series = series.rename(columns = {'Unnamed: 0': 'Season'})
+series['Id'] = series.Season.str.extract(r'(s\d+)(|\',\ )(\d+)')[0]
+series.Season = series.Season.str.extract(r'(s\d+)(|\',\ )(\d+)')[2].astype('int32')
+series = series[series.Season > 0]
+
+mlb = MultiLabelBinarizer()
+
+series = series.join(pd.DataFrame(mlb.fit_transform(series.pop('listed_in').str.split(', ')),
+                          columns=mlb.classes_,
+                          index=series.index))
+
+series_train, series_test = sklearn.model_selection.train_test_split(series,test_size=0.20, random_state=42)
+series_test, series_val = sklearn.model_selection.train_test_split(series_test,test_size=0.50, random_state=42)
+
+series_subsets = [series_train, series_test, series_val]
+for subset in series_subsets:
+    print(subset.shape[0])
+    print(subset.describe(include='all'))
+
+series_subsets = pd.concat(series_subsets, keys = ['Train','Test','Validation'])
+series_subsets = series_subsets.reset_index()
+ax = sns.boxplot(data = series_subsets, x = 'level_0', y = 'rottentomatoes_audience_score')
+ax.set(title = 'Audience score distribution between subsets', ylabel = 'Audience score on Rotten Tomatoes', xlabel = 'SUBSET')
+plt.show(ax)

run.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+kaggle kernels output 'eugenioscionti/scraping-rotten-tomatoes-to-enrich-netflix-dataset'
+python ium_zadanie1.py