离散型变量的数据分析

import pandas as pd
pd.set_option('display.max_column',30)
import numpy as np
import statsmodels.api as sm
import matplotlib.pyplot as plt
import seaborn as sns
sns.set()

from pylab import rcParams ##matplotlib
rcParams['figure.figsize'] = 12, 8

import warnings 
warnings.filterwarnings('ignore')

from pyecharts import options as opts
from pyecharts.charts import Bar, Line, Pie, Map, Page, ThemeRiver, Timeline, Grid
from pyecharts.commons.utils import JsCode

train = pd.read_csv('./first_round_training_data.csv')[['Parameter'+str(i) for i in range(1,11)]+['Quality_label']].round(5)
test = pd.read_csv('./first_round_testing_data.csv').round(5)
feature = ['Parameter'+str(i) for i in range(1,11)]

print(train.head())

   Parameter1  Parameter2  Parameter3  Parameter4  Parameter5  Parameter6  \
0     0.0