python pandas借助pandas-profiling自动生成EDA

安装方法：

pip install pandas-profiling

github地址：https://github.com/pandas-profiling/pandas-profiling

示例代码

import numpy as np
import pandas as pd
from pandas_profiling import ProfileReport


# pip install pandas-profiling
def load_data():
    """用来生成训练、测试数据"""
    from sklearn.datasets import make_classification
    data_x, data_y = make_classification(n_samples=1000, n_classes=4, n_features=10, n_informative=8)
    df_x = pd.DataFrame(data_x, columns=['f_1', 'f_2', 'f_3', 'f_4', 'f_5', 'f_6', "f_7", "f_8", "f_9", "f_10"])
    df_y = pd.Series(data_y)
    return df_x, df_y


if __name__ == '__main__':
    x_data, y_data = load_data()
    pfr = ProfileReport(x_data)
    pfr.to_file('report.html')