二、数据了解与分析

import warnings
warnings.filterwarnings('ignore')
# import missingno as msno
import pandas as pd
from pandas import DataFrame
import matplotlib.pyplot as plt 
import seaborn as sns
import numpy as np

Train_data = pd.read_csv('./train.csv')

Test_data = pd.read_csv('./testA.csv')

Train_data.head().append(Train_data.tail

Train_data.shape

(100000, 3)

Test_data.head().append(Test_data.tail())

Test_data.shape

(20000, 2)

Train_data.describe()

Train_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 100000 entries, 0 to 99999
Data columns (total 3 columns):
id                   100000 non-null int64
heartbeat_signals    100000 non-null object
label                100000 non-null float64
dtypes: float64(1), int64(1), object(1)
memory usage: 2.3+ MB

Test_data.describe()

Test_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 20000 entries, 0 to 19999
Data columns (total 2 columns):
id                   20000 non-null int64
heartbeat_signals    20000 non-null object
dtypes: int64(1), object(1)
memory usage: 312.6+ KB

Train_data.isnull().sum()

id                   0
heartbeat_signals    0
label                0
dtype: int64

Train_data['label'].value_counts()

0.0    64327
3.0    17912
2.0    14199
1.0     3562
Name: label, dtype: int64

## 1) 总体分布概况（无界约翰逊分布等）
import scipy.stats as st
y = Train_data['label']
plt.figure(1); plt.title('Default')
sns.distplot(y, rug=True, bins=20)
plt.figure(2); plt.title('Normal')
sns.distplot(y, kde=False, fit=st.norm)
plt.figure(3); plt.title('Log Normal')
sns.distplot(y, kde=False, fit=st.lognorm)

<matplotlib.axes._subplots.AxesSubplot at 0x26849b6c448>

# 2）查看skewness and kurtosis
sns.distplot(Train_data['label']);
print("Skewness: %f" % Train_data['label'].skew())
print("Kurtosis: %f" % Train_data['label'].kurt())

Skewness: 0.871005
Kurtosis: -1.009573

Train_data.skew(), Train_data.kurt()

(id       0.000000
 label    0.871005
 dtype: float64, id      -1.200000
 label   -1.009573
 dtype: float64)

sns.distplot(Train_data.kurt(),color='orange',axlabel ='Kurtness')

<matplotlib.axes._subplots.AxesSubplot at 0x2684ad75bc8>

## 3) 查看预测值的具体频数
plt.hist(Train_data['label'], orientation = 'vertical',histtype = 'bar', color ='red')
plt.show()

import pandas_profiling

pfr = pandas_profiling.ProfileReport(Train_data)
pfr.to_file("./example.html")