Added docstrigs

app.py

@@ -6,19 +6,17 @@ from surprise import Dataset, Reader
 from surprise import KNNBasic
 
 def opendata(a, nrows):
+    """
+    opens the data and returns a dataframe
+    """
     df = pd.read_csv(a, nrows=nrows, sep=';', encoding='ISO-8859-1')
     return df
 
-def split(df):
-    n=len(df)
-    N=list(range(n))
-    random.seed(2023)
-    random.shuffle(N)
-    train=df.iloc[N[0:(n*4)//5]]
-    test=df.iloc[N[(n*4)//5:]]
-    return train, test
-
 def red(df):
+    """
+    Builds the trainset and the anti testset,
+    Returns the trainset and the anti testset as items
+    """
     reader = Reader(rating_scale=(1,10)) # rating scale range
     trainset = Dataset.load_from_df(df[['User-ID','ISBN','Book-Rating']],reader).build_full_trainset()
     items = trainset.build_anti_testset()
@@ -26,6 +24,12 @@ def red(df):
 
 
 def mod(df, user, items):
+    """
+    Builds the model using KNNBasic,
+    Fits the model to the trainset,
+    Takes the given user and creates a recommendation for them based on the model
+    returns the recommendations
+    """
     algo = KNNBasic()
     algo.fit(df)
     user_items = list(filter(lambda x: x[0] == user, items))
@@ -34,12 +38,18 @@ def mod(df, user, items):
     return recommendations
 
 def gl(num):
+    """
+    Opens the 2 datasets
+    Creates a mapping dictionary for the ISBN and Book-Title,
+    Creates a list of users and accepts a user input,
+    Builds the model and returns the top 5 recommendations for the user
+    """
     data = opendata('BX-Book-Ratings.csv', nrows=20_000)
     books = opendata('BX_Books.csv', nrows=None)
     mapping_dict = books.set_index("ISBN")["Book-Title"].to_dict()
-    train, test = split(data)
-    users=test['User-ID'].tolist()
-    trainset, items  = red(train)
+
+    users=data['User-ID'].tolist()
+    trainset, items  = red(data)
     user = users[int(num)]
     recommendations = mod(trainset, user, items)
     op = []