Separate each part of the lab in a folder

src/P2/preprocessing.py

@@ -0,0 +1,49 @@
+from pandas import read_csv
+from sklearn.model_selection import KFold
+from sklearn.preprocessing import LabelEncoder
+
+
+def replace_values(df):
+    columns = ["BI-RADS", "Margin", "Density", "Age"]
+    for column in columns:
+        df[column].fillna(value=df[column].mean(), inplace=True)
+    return df
+
+
+def process_na(df, action):
+    if action == "drop":
+        return df.dropna()
+    elif action == "fill":
+        return replace_values(df)
+    else:
+        print("Unknown action selected. The choices are: ")
+        print("fill: fills the na values with the mean")
+        print("drop: drops the na values")
+        exit()
+
+
+def encode_columns(df):
+    label_encoder = LabelEncoder()
+    encoded_df = df.copy()
+    encoded_df["Shape"] = label_encoder.fit_transform(df["Shape"])
+    encoded_df["Severity"] = label_encoder.fit_transform(df["Severity"])
+    return encoded_df
+
+
+def split_train_target(df):
+    train_data = df.drop(columns=["Severity"])
+    target_data = df["Severity"]
+    return train_data, target_data
+
+
+def split_k_sets(df):
+    k_fold = KFold(shuffle=True, random_state=42)
+    return k_fold.split(df)
+
+
+def parse_data(source, action):
+    df = read_csv(filepath_or_buffer=source, na_values="?")
+    processed_df = process_na(df=df, action=action)
+    encoded_df = encode_columns(df=processed_df)
+    test_data, target_data = split_train_target(df=encoded_df)
+    return test_data, target_data