Exemplo n.º 1
0
def evaluate_fix_classifier():

    text_name = 'message'
    classification_function = is_fix
    classification_column = 'corrective_pred'

    concept_column = 'Is_Corrective'

    df = pd.read_csv(join(DATA_PATH, 'corrective_texts_tests.csv'))

    #df = df[df.certain != 'FALSE']
    df = df[~df.Is_Corrective.isna()]

    #concept_column='is_corrective'
    #df = pd.read_csv("/Users/idan/playground/commit-classification/data/change_samples.csv")

    df = classifiy_commits_df(df,
                              classification_function=classification_function,
                              classification_column=classification_column,
                              text_name=text_name)
    cm = evaluate_performance(df,
                              classification_column,
                              concept_column,
                              text_name=text_name)
    print("corrective_labels CM")
    print(cm)
    df = df[(df['disable'] != 1)]
    """
    fp = get_false_positives(df
                        , classifier_column=classification_column
                        , concept_column=concept_column)
    print("False Positives")
    pd.options.display.max_columns = 50
    pd.options.display.max_rows = 2000
    print(fp)

    """
    fn = get_false_negatives(df,
                             classifier_column=classification_column,
                             concept_column=concept_column)
    print("False Negatives")
    pd.options.display.max_columns = 50
    pd.options.display.max_rows = 2000
    print(fn)
Exemplo n.º 2
0
def evaluate_cc_fix_classifier():
    text_name = 'message'
    classification_function = is_cc_corrective
    classification_column = 'corrective_pred'

    concept_column = 'Is_Corrective'

    df = pd.read_csv(join(DATA_PATH, 'conventional_commits.csv'))

    df = classifiy_commits_df(df,
                              classification_function=classification_function,
                              classification_column=classification_column,
                              text_name=text_name)
    cm = evaluate_performance(df,
                              classification_column,
                              concept_column,
                              text_name=text_name)
    print("corrective_labels CM")
    print(cm)
Exemplo n.º 3
0
def evaluate_abstraction_classifier():
    text_name = 'message'
    classification_function = is_abstraction
    classification_column = 'abstraction_pred'

    concept_column = 'Is_abstraction'

    df = pd.read_csv(join(DATA_PATH, 'abstraction_commits.csv'))

    df = classifiy_commits_df(df,
                              classification_function=classification_function,
                              classification_column=classification_column,
                              text_name=text_name)
    cm = evaluate_performance(df,
                              classification_column,
                              concept_column,
                              text_name=text_name)
    print("Abstraction labels CM")
    print(cm)
Exemplo n.º 4
0
def evaluate_adaptive_classifier():
    text_name = 'message'
    classification_function = is_adaptive
    classification_column = 'corrective_pred'

    concept_column = 'Is_Adaptive'

    df = pd.read_csv(join(DATA_PATH, 'commit_classification_batch2.csv'))
    df = df[df.certain != 'FALSE']
    df = df[~df.Is_Corrective.isna()]
    """
    concept_column = 'is_adaptive'
    df = pd.read_csv(join(DATA_PATH, "commit_classification_batch2.csv"))
    df[concept_column] = df.expected.map(lambda x: not x)
    """
    df = classifiy_commits_df(df,
                              classification_function=classification_function,
                              classification_column=classification_column,
                              text_name=text_name)
    cm = evaluate_performance(df,
                              classification_column,
                              concept_column,
                              text_name=text_name)
    print("corrective_labels CM")
    print(cm)
    """
    fp = get_false_positives(df
                             , classifier_column=classification_column
                             , concept_column=concept_column)
    print("False Positives")
    pd.options.display.max_columns = 50
    pd.options.display.max_rows = 2000
    print(fp)

    """
    fn = get_false_negatives(df,
                             classifier_column=classification_column,
                             concept_column=concept_column)
    print("False Negatives")
    pd.options.display.max_columns = 50
    pd.options.display.max_rows = 2000
    print(fn)