Add preprocessing module

src/preprocessing.py

@@ -0,0 +1,26 @@
+from pandas import read_csv
+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()
+    return replace_values(df)
+
+
+def encode_columns(df):
+    encoder = LabelEncoder()
+    encoder.fit(df["Shape"])
+
+
+def parse_data(source, action):
+    df = read_csv(filepath_or_buffer=source, na_values="?")
+    processed_df = process_na(df, action)
+    return processed_df

src/processing.py

@@ -0,0 +1 @@
+from preprocessing import parse_data