Upload app.py

app.py

@@ -0,0 +1,116 @@
+# -*- coding: utf-8 -*-
+"""HS_Surprise Module_Metacritic_Games_Recomm.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/1sZ9FI7bnnNBcvFa2rt78EKYeU2L4XrXi
+"""
+
+!pip install surprise
+
+from surprise import NMF, SVD, SVDpp, KNNBasic, KNNWithMeans, KNNWithZScore, CoClustering
+from surprise.model_selection import cross_validate
+from surprise import Reader, Dataset
+
+!pip install gradio
+
+import gradio as gr
+
+import pandas as pd
+import numpy as np
+import scipy as sp
+from scipy import sparse
+from datetime import datetime
+
+df = pd.read_csv("/content/metacritic_critic_reviews.csv", on_bad_lines='skip', encoding="utf-8")
+df.dropna(inplace=True)
+df.head()
+
+#Create date column by converting the date into a datetime object then returning only the year
+def add_year(full_date):
+  datetime_object = datetime.strptime(full_date, '%b %d, %Y')
+  return datetime_object.year
+
+df['year'] = df['date'].apply(add_year)
+#Add the year in brackets to the name of the game to avoid confusion 
+def year_game(row):
+  calendar_year = str(row['year'])
+  year_game_combined = str(row['game']) + " (" + calendar_year + ")"
+  return year_game_combined
+
+df['game'] = df.apply(year_game, axis=1)
+
+#['PC', '3DS', 'PlayStation Vita', 'Wii U', 'PlayStation 4','Xbox One', 'Switch']
+df = df[df['platform'] == 'PlayStation 4']
+
+#Filter by games since 2015 onwards
+over_2015 = df[df['year'] >= 2015]
+
+#Group by average score then sort by descending
+top_recent_scorers = over_2015.groupby('game')['score'].mean().sort_values(ascending=False)
+#Only show top 20 games
+top_40_games = top_recent_scorers.index[:40]
+#top_100_games = top_recent_scorers.index[:100]
+
+df.shape
+
+combined_games_data = df[['game','name','score']]
+algorithms = [NMF(), SVD(), SVDpp(), KNNWithZScore(), CoClustering()]
+
+def recommender(user_prof, user_algo=KNNWithZScore(), combined_games_data=combined_games_data): # top_100_games=top_100_games, 
+
+  my_ratings = user_prof[user_prof['score'] != 0]
+  combined_games_data = pd.concat([combined_games_data, my_ratings], axis=0)
+  combined_games_data.columns = ['itemID', 'userID', 'rating']
+
+  # use the transform method group by userID and count to keep the games with more than reviews within user profile. Ideally 20 or more.
+  combined_games_data['reviews'] = combined_games_data.groupby(['itemID'])['rating'].transform('count')
+  combined_games_data = combined_games_data[combined_games_data.reviews>=my_ratings.shape[0]][['userID', 'itemID', 'rating']]
+
+  reader = Reader(rating_scale=(1.0, 100.0))
+  data = Dataset.load_from_df(combined_games_data, reader)
+
+  unique_ids = combined_games_data['itemID'].unique()
+
+  iids1001 = combined_games_data.loc[combined_games_data['userID']==1001, 'itemID']
+
+  games_to_predict = np.setdiff1d(unique_ids,iids1001)
+
+  for i in range(len(algorithms)):
+    if i == 'NMF':
+      user_algo = NMF()
+    elif i == 'SVD':
+      user_algo = SVD()
+    elif i == 'SVDpp':
+      user_algo = SVDpp()
+    elif i == 'KNN':
+      user_algo = KNNWithZScore()
+    elif i == 'CoClustering':
+      user_algo = CoClustering()
+    else:
+      user_algo = NMF()
+
+  algo = user_algo
+  algo.fit(data.build_full_trainset())
+
+  my_recs = []
+  for iid in games_to_predict:
+      my_recs.append((iid, algo.predict(uid=1001,iid=iid).est))
+      
+  result = pd.DataFrame(my_recs, columns=['iid', 'predictions']).sort_values('predictions', ascending=False).head(10)
+  return result
+
+default_entries = []
+for record in range(len(top_40_games)):
+  default_entries.append([top_40_games[record], 1001, 0])
+
+iface = gr.Interface(recommender, 
+    inputs=[gr.inputs.Dataframe(
+        headers=['game','name','score'],
+        default=default_entries
+    ), 
+    gr.inputs.Radio(['NMF', 'SVD', 'SVDpp', 'KNN', 'CoClustering'])],
+    outputs="dataframe",
+)
+iface.launch(debug=True)