Added counting of data

pipeline.py

@@ -77,10 +77,24 @@ def make_sequences(data, sequence_length):
 
 def prepare_data_for_model(user_data, sequence_length):
     x, y = [], []
+    combined = pd.DataFrame()
     for user, data in user_data.items():
         x_new, y_new = make_sequences(data, sequence_length)
         x = x + x_new
         y = y + y_new
+        if len(x_new)>0:
+            var = [[pd.DataFrame(a[s])for s in range(sequence_length)] for a in x_new ]
+            df_var = pd.concat([pd.concat(seq_list).T for seq_list in var])
+            df_var['user'] = user
+            combined = pd.concat([combined, df_var], ignore_index=True)
+    combined_ohne = combined.drop('user', axis=1)
+    print('Alle', len(combined))
+    print('Unique mit user', len(combined.drop_duplicates()))
+    print('Unique ohne user', len(combined_ohne.drop_duplicates()))
+    print('Unique')
+    print(combined.drop_duplicates()['user'].value_counts())
+    print('Alle')
+    print(combined['user'].value_counts())
     random.Random(17).shuffle(x)
     random.Random(17).shuffle(y)
     x = np.array(x)