Final push of the day

app.py

@@ -111,6 +111,34 @@ price_ranges_labels = [
     "$40 - $49.99",
     "$50+"               
 ]
+df_games_temp = df_games
+df_games_temp = col_to_list(df_games_temp,'Genres')
+df_games_temp = col_to_list(df_games_temp,'Categories')
+df_games_temp = apply_price_range_labels(df_games_temp,price_ranges_labels,price_bins)
+df_games_temp['Year_Release'] = df_games_temp['Release date'].apply(extract_year)
+df_games_temp['Game score'] = np.where(
+    (df_games_temp['Positive'] + df_games_temp['Negative']) == 0,
+    0,
+    (df_games_temp['Positive'] / (df_games_temp['Positive'] + df_games_temp['Negative'])) * 100
+)
+genre_mlb = MultiLabelBinarizer()
+genre_mlb = genre_mlb.fit(df_games_temp['Genres'])
+categories_mlb = MultiLabelBinarizer()
+categories_mlb = categories_mlb.fit(df_games_temp['Categories'])
+price_range_le = model.game_content_recommeder.price_range_encoder
+scaler = MinMaxScaler()
+scaler = scaler.fit(df_games_temp[['Year_Release','Average playtime forever','Game score','DLC count']].values)
+app_id_le = LabelEncoder()
+app_id_le = app_id_le.fit(df_games_temp['app_id'])
+numerical_col =['Year_Release','Average playtime forever','Game score','DLC count']
+
+genre_matrix = genre_mlb.transform(df_games_temp['Genres'])
+genre_df = pd.DataFrame(genre_matrix, columns=genre_mlb.classes_, index=df_games_temp.index)
+categories_matrix = categories_mlb.transform(df_games_temp['Categories'])
+categories_df = pd.DataFrame(categories_matrix,columns=categories_mlb.classes_,index=df_games_temp.index)
+game_df = pd.concat([df_games_temp[['app_id','Price_range']+numerical_col],genre_df,categories_df],axis=1)
+game_df['Price_range'] = price_range_le.transform(game_df['Price_range'])
+game_df[numerical_col] = scaler.transform(game_df[numerical_col].values)
 
 def recommend_game(description=None, app_name=None, price_range=None, year_release=None,
             excpected_playtime=None, game_score=None, dlc_count=None, 
@@ -340,11 +368,11 @@ df_games_raw['Developers'] = df_games_raw['Developers'].fillna('')
 df_games_raw['Publishers'] = df_games_raw['Publishers'].fillna('')
 df_games_raw.to_csv('Cleaned_games.csv',index=False)
 """)
-                h2('Games Data Cleaned')
-                gr.Dataframe(df_games.head(20))
+                # h2('Games Data Cleaned')
+                # gr.Dataframe(df_games.head(20))
                 
                 h2('2.2. Review Preprocessing')
-                Dataset(df_review_raw,'Review Data Raw',REVIEWS_DATAPATH)
+                # Dataset(df_review_raw,'Review Data Raw',REVIEWS_DATAPATH)
                 code_cell("""
 from nltk.tokenize import word_tokenize
 from nltk.corpus import stopwords
@@ -869,7 +897,7 @@ df = col_to_list(df,'Genres')
 df = col_to_list(df,'Categories')
 df = apply_price_range_labels(df,price_labels,price_bins)
                           """)
-                Dataset(df_games,"The game dataset",GAMES_DATAPATH)
+                # Dataset(df_games,"The game dataset",GAMES_DATAPATH)
                 
                 code_cell("""
 def extract_year(date_str):
@@ -885,36 +913,7 @@ df['Game score'] = np.where(
     0,
     (df['Positive'] / (df['Positive'] + df['Negative'])) * 100
 )""")
-                def game_df_create():
-                    df_games_temp = df_games
-                    df_games_temp = col_to_list(df_games_temp,'Genres')
-                    df_games_temp = col_to_list(df_games_temp,'Categories')
-                    df_games_temp = apply_price_range_labels(df_games_temp,price_ranges_labels,price_bins)
-                    df_games_temp['Year_Release'] = df_games_temp['Release date'].apply(extract_year)
-                    df_games_temp['Game score'] = np.where(
-                        (df_games_temp['Positive'] + df_games_temp['Negative']) == 0,
-                        0,
-                        (df_games_temp['Positive'] / (df_games_temp['Positive'] + df_games_temp['Negative'])) * 100
-                    )
-                    genre_mlb = MultiLabelBinarizer()
-                    genre_mlb = genre_mlb.fit(df_games_temp['Genres'])
-                    categories_mlb = MultiLabelBinarizer()
-                    categories_mlb = categories_mlb.fit(df_games_temp['Categories'])
-                    price_range_le = model.game_content_recommeder.price_range_encoder
-                    scaler = MinMaxScaler()
-                    scaler = scaler.fit(df_games_temp[['Year_Release','Average playtime forever','Game score','DLC count']].values)
-                    app_id_le = LabelEncoder()
-                    app_id_le = app_id_le.fit(df_games_temp['app_id'])
-                    numerical_col =['Year_Release','Average playtime forever','Game score','DLC count']
-                    
-                    genre_matrix = genre_mlb.transform(df_games_temp['Genres'])
-                    genre_df = pd.DataFrame(genre_matrix, columns=genre_mlb.classes_, index=df_games_temp.index)
-                    categories_matrix = categories_mlb.transform(df_games_temp['Categories'])
-                    categories_df = pd.DataFrame(categories_matrix,columns=categories_mlb.classes_,index=df_games_temp.index)
-                    game_df = pd.concat([df_games_temp[['app_id','Price_range']+numerical_col],genre_df,categories_df],axis=1)
-                    game_df['Price_range'] = price_range_le.transform(game_df['Price_range'])
-                    game_df[numerical_col] = scaler.transform(game_df[numerical_col].values)
-                    return game_df.head(10)
+                
                 code_cell("""
 from sklearn.preprocessing import MultiLabelBinarizer,LabelEncoder,MinMaxScaler
 genre_mlb = MultiLabelBinarizer()
@@ -936,9 +935,9 @@ categories_matrix = categories_mlb.transform(df['Categories'])
 categories_df = pd.DataFrame(categories_matrix,columns=categories_mlb.classes_,index=df.index)
 game_df = pd.concat([df[['app_id','Price_range']+numerical_col],genre_df,categories_df],axis=1)""")
 
-                btn = gr.Button("Run game_df preprocess")
-                output_game_df = gr.Dataframe()
-                btn.click(fn=game_df_create, inputs=None, outputs=output_game_df)
+                gr.Dataframe(df_games_temp.head(10))
+                del df_games_temp
+                gc.collect()
                 code_cell("""
 from sklearn.neighbors import KNeighborsClassifier
 X = game_df.loc[:,['Year_Release','Average playtime forever','Game score','DLC count','Price_range']+ list(genre_mlb.classes_) + list(categories_mlb.classes_)]