Update model.py

model.py

@@ -157,7 +157,7 @@ def playlist_model(url, model, max_gen=3, same_art=5):
          log.append('Model run successfully')
          return Fresult, log
 
-     lendf=len(pd.read_csv('../data/streamlit.csv',usecols=['track_uri']))
+     lendf=len(pd.read_csv('data/streamlit.csv',usecols=['track_uri']))
      dtypes = {'track_uri': 'object', 'artist_uri': 'object', 'album_uri': 'object', 'danceability': 'float16', 'energy': 'float16', 'key': 'float16',
                'loudness': 'float16', 'mode': 'float16', 'speechiness': 'float16', 'acousticness': 'float16', 'instrumentalness': 'float16',
                'liveness': 'float16', 'valence': 'float16', 'tempo': 'float16', 'duration_ms': 'float32', 'time_signature': 'float16',
@@ -292,7 +292,7 @@ def playlist_model(url, model, max_gen=3, same_art=5):
      x = 1
      for i in range(int(lendf/2), lendf+1, int(lendf/2)):
          try:
-             df = pd.read_csv('../data/streamlit.csv',names= col_name,dtype=dtypes,skiprows=x,nrows=i)
+             df = pd.read_csv('data/streamlit.csv',names= col_name,dtype=dtypes,skiprows=x,nrows=i)
              log.append('reading data frame chunks from {} to {}'.format(x,i))
          except Exception as e:
              log.append('Failed to load grow')
@@ -315,7 +315,7 @@ def playlist_model(url, model, max_gen=3, same_art=5):
              log.append('genre|unknown not found')
          log.append('Scaling the data .....')
          if x == 1:
-             sc = pickle.load(open('../data/sc.sav','rb'))
+             sc = pickle.load(open('data/sc.sav','rb'))
              df.iloc[:, 3:19] = sc.transform(df.iloc[:, 3:19])
              test.iloc[:, 3:19] = sc.transform(test.iloc[:, 3:19])
              log.append("Creating playlist vector")
@@ -359,13 +359,13 @@ def playlist_model(url, model, max_gen=3, same_art=5):
      log.append('{} New Tracks Found'.format(len(grow)))
      if(len(grow)>=1):
         try:
-            new=pd.read_csv('../data/new_tracks.csv',dtype=dtypes)
+            new=pd.read_csv('data/new_tracks.csv',dtype=dtypes)
             new=pd.concat([new, grow], axis=0)
             new=new[new.Track_pop >0]
             new.drop_duplicates(subset=['track_uri'], inplace=True,keep='last')
-            new.to_csv('../data/new_tracks.csv',index=False)
+            new.to_csv('data/new_tracks.csv',index=False)
         except:
-            grow.to_csv('../data/new_tracks.csv', index=False)
+            grow.to_csv('data/new_tracks.csv', index=False)
      log.append('Model run successfully')
     except Exception as e:
         log.append("Model Failed")
@@ -437,7 +437,7 @@ def song_model(url, model, max_gen=3, same_art=5):
             Fresult.append(aa['tracks'][i]['id'])
         log.append('Model run successfully')
         return Fresult, log
-     lendf=len(pd.read_csv('../data/streamlit.csv',usecols=['track_uri']))
+     lendf=len(pd.read_csv('data/streamlit.csv',usecols=['track_uri']))
      dtypes = {'track_uri': 'object', 'artist_uri': 'object', 'album_uri': 'object', 'danceability': 'float16', 'energy': 'float16', 'key': 'float16',
                'loudness': 'float16', 'mode': 'float16', 'speechiness': 'float16', 'acousticness': 'float16', 'instrumentalness': 'float16',
                'liveness': 'float16', 'valence': 'float16', 'tempo': 'float16', 'duration_ms': 'float32', 'time_signature': 'float16',
@@ -504,7 +504,7 @@ def song_model(url, model, max_gen=3, same_art=5):
      x = 1
      for i in range(int(lendf/2), lendf+1, int(lendf/2)):
          try:
-             df = pd.read_csv('../data/streamlit.csv',names= col_name,dtype=dtypes,skiprows=x,nrows=i)
+             df = pd.read_csv('data/streamlit.csv',names= col_name,dtype=dtypes,skiprows=x,nrows=i)
              log.append('reading data frame chunks from {} to {}'.format(x,i))
          except Exception as e:
              log.append('Failed to load grow')
@@ -527,7 +527,7 @@ def song_model(url, model, max_gen=3, same_art=5):
              log.append('genre|unknown not found')
          log.append('Scaling the data .....')
          if x == 1:
-             sc = pickle.load(open('../data/sc.sav','rb'))
+             sc = pickle.load(open('data/sc.sav','rb'))
              df.iloc[:, 3:19] = sc.transform(df.iloc[:, 3:19])
              test.iloc[:, 3:19] = sc.transform(test.iloc[:, 3:19])
              log.append("Creating playlist vector")
@@ -571,13 +571,13 @@ def song_model(url, model, max_gen=3, same_art=5):
      log.append('{} New Tracks Found'.format(len(grow)))
      if(len(grow)>=1):
         try:
-            new=pd.read_csv('../data/new_tracks.csv',dtype=dtypes)
+            new=pd.read_csv('data/new_tracks.csv',dtype=dtypes)
             new=pd.concat([new, grow], axis=0)
             new=new[new.Track_pop >0]
             new.drop_duplicates(subset=['track_uri'], inplace=True,keep='last')
-            new.to_csv('../data/new_tracks.csv',index=False)
+            new.to_csv('data/new_tracks.csv',index=False)
         except:
-            grow.to_csv('../data/new_tracks.csv', index=False)
+            grow.to_csv('data/new_tracks.csv', index=False)
      log.append('Model run successfully')
     except Exception as e:
         log.append("Model Failed")
@@ -593,14 +593,14 @@ def update_dataset():
                'loudness': 'float16', 'mode': 'float16', 'speechiness': 'float16', 'acousticness': 'float16', 'instrumentalness': 'float16',
                'liveness': 'float16', 'valence': 'float16', 'tempo': 'float16', 'duration_ms': 'float32', 'time_signature': 'float16',
                'Track_release_date': 'int8', 'Track_pop': 'int8', 'Artist_pop': 'int8', 'Artist_genres': 'object'}
-    df = pd.read_csv('../data/streamlit.csv',dtype=dtypes)
-    grow = pd.read_csv('../data/new_tracks.csv',dtype=dtypes)
+    df = pd.read_csv('data/streamlit.csv',dtype=dtypes)
+    grow = pd.read_csv('data/new_tracks.csv',dtype=dtypes)
     cur = len(df)
     df=pd.concat([df,grow],axis=0)
     grow=pd.DataFrame(columns=col_name)
-    grow.to_csv('../data/new_tracks.csv',index=False)
+    grow.to_csv('data/new_tracks.csv',index=False)
     df=df[df.Track_pop >0]
     df.drop_duplicates(subset=['track_uri'],inplace=True,keep='last')
     df.dropna(axis=0,inplace=True)
-    df.to_csv('../data/streamlit.csv',index=False)
+    df.to_csv('data/streamlit.csv',index=False)
     return (len(df)-cur)