pandas_profiling 数据报表展示

最新推荐文章于 2024-04-25 09:33:18 发布

原创最新推荐文章于 2024-04-25 09:33:18 发布 · 1.1k 阅读

1 ·

CC 4.0 BY-SA版权

Python 专栏收录该内容

30 篇文章

订阅专栏

本文介绍了一种使用Python进行数据预处理和可视化的实践案例。通过对数据集进行加载、清洗、特征工程处理（如权重分类）并利用Pandas Profiling生成详细的分析报告，展示了如何有效地准备数据并进行初步的探索性分析。

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")