pandas_profiling 数据报表展示



from __future__ import absolute_import,division,print_function
import matplotlib as mpl
import matplotlib.pyplot as plt
from matplotlib.pyplot import GridSpec
import seaborn as sns
import numpy as np
import pandas as pda
import os ,sys
from tqdm import tqdm
import warnings
warnings.filterwarnings("ignore")
sns.set_context("poster",font_scale=1.3)
import missingno as msno
import pandas_profiling
from sklearn.datasets import make_blobs
import time
#读入数据
data=pda.read_csv("redcard.csv.gz",compression="gzip")
print("=============多变量分析=========")

# from pandas.tools.plotting import scatter_matrix
# fig,ax=plt.subplots(figsize=(10,10))
# scatter_matrix(players[["height","weight","skinone"]],alpha=0.2,diagonal="hist",ax=ax)
# players=pda.read_csv("raw_players.csv.gz")
# players=players[players["rater1"].notnull()]
# print(players.head())
weight_categories=["vlow_weight","low_weight","mid_weight",
                   "high_weight","vhigh_weight",]
data["weight_class"]=pda.qcut(data["weight"],len(weight_categories),weight_categories)
print(data.head())
# windows pycharm执行代码,执行完在浏览器打开example.html
if __name__ == '__main__':
   pfr = pandas_profiling.ProfileReport(data)
   pfr.to_file("./example.html")