MachineLearning.py 文件源码

def describe_data(data, info=False, describe=False, value_counts=None, unique=None,
                  univariate_feature_selection=None, description=None):
    # Data diagnostics
    if description is not None:
        print("\n" + description)

    # Info
    if info:
        print("\nInfo:")
        print(data.info())

    # Description
    if describe:
        print("\nDescribe:")
        print(data.describe())

    # Value counts
    if value_counts is not None:
        for feature in value_counts:
            print("\nValue Counts [" + feature + "]")
            print(pd.value_counts(data[feature]))

    # Unique values
    if unique is not None:
        for feature in unique:
            print("\nUnique [" + feature + "]")
            print(data[feature].unique())

    # Univariate feature selection
    if univariate_feature_selection is not None:
        # Extract predictors and target
        predictors = univariate_feature_selection[0]
        target = univariate_feature_selection[1]

        # Perform feature selection
        selector = SelectKBest(f_classif, k="all")
        selector.fit(data[predictors], data[target])

        # Get the raw p-values for each feature, and transform from p-values into scores
        scores = -np.log10(selector.pvalues_)
        print("\nUnivariate Feature Selection:")
        for feature, imp in sorted(zip(predictors, scores), key=lambda x: x[1] if pd.notnull(x[1]) else 0):
            print(feature, imp)