snapshot...

modules/machine_learning/classification.py

@@ -12,8 +12,11 @@ from sklearn.tree import DecisionTreeClassifier
 import sklearn.tree as tree
 
 
-def get_csv_as_dataframe(csv_file):
+def get_csv_as_dataframe(csv_file, reduce_frac=None):
     icing_df = pd.read_csv(csv_file)
+    # Random selection of reduce_frac of the rows
+    if reduce_frac is not None:
+        icing_df = icing_df.sample(frac=reduce_frac)
     print(icing_df.describe())
     print(icing_df.shape)
     return icing_df