combine_classification_with_the_num.py

for j, i in enumerate(targets_all):
    remove_redundant_list = list(targets_all)
    remove_redundant_list.remove(i)
    
    new_column_classification = i + "_classification"
    # first let's create a new column with the 150days prediction classifier: 0 when price dropped and 1 when it's increased.
    df_compact_reserve.loc[df_compact_reserve[i]<0.01, new_column_classification] = 0
    df_compact_reserve.loc[df_compact_reserve[i]>=0.01, new_column_classification] = 1

    #let's join prediction result to the test dataframe and get indexes
    df_prediction = list_of_test_df[j].copy()
    df_prediction["prediction"] = list_of_ypred[j]
    df_prediction = df_prediction["prediction"]

    #let's connect prediction result by indexes to the main dataframe
    df_compare =  df_compact_reserve[[i,new_column_classification]]
    df_compare = df_compare.join(df_prediction, how = 'left')
    df_compare = df_compare[df_compare["prediction"].notnull()]

    # Now let's see how many negative values were really predicted as positive
    df_compare = df_compare[[new_column_classification,"prediction"]].groupby(new_column_classification).sum()
    df_compare["Value, %"] = (df_compare['prediction'] / df_compare['prediction'].sum()) * 100
    print(f"{i} precision is ")
    print(str(round(df_compare["Value, %"][1],2)) + "%\n")