python大数据分析

数据分析：Python的Pandas库数据处理 #生活知识# #编程教程#

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

83

84

85

86

87

88

89

90

91

92

93

94

95

96

97

98

99

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

!pip install xgboost

import pandas as pd

import numpy as np

import seaborn as sns

import matplotlib.pyplot as plt

from sklearn.preprocessing import LabelEncoder

import warnings

import xgboost

from sklearn.model_selection import train_test_split

from sklearn.ensemble import RandomForestRegressor,RandomForestClassifier

from sklearn.metrics import confusion_matrix, classification_report, accuracy_score

warnings.filterwarnings('ignore')

plt.rcParams['font.sans-serif'] = ['Microsoft YaHei']

df = pd.read_csv('/home/mw/input/data1581/Sleep_health_and_lifestyle_dataset.csv',encoding='gbk')

df.head()

df.info()

df.duplicated().sum()df_new = df.copy()cat_cols = []for each in df_new.columns.tolist():

    if df_new[each].dtype == 'object' and each != '血压':

        cat_cols.append(each)

        print(df_new[each].value_counts().to_frame())

    le = LabelEncoder()

    le.fit(df_new[col])

    df_new[col] = le.transform(df_new[col])df_new.head()xueya = df_new['血压'].str.split('/',expand=True)

xueya.columns = ['高压','低压']

xueya = xueya.astype(int)df_new = pd.concat([df_new,xueya],axis=1)df_new.info()plt.figure(figsize=(12,8))

sns.countplot(x='性别',hue='职业',data=df,palette='Set3')

plt.title('男女及从事职业情况',fontsize=20)

plt.show()plt.figure(figsize=(12,8))

sns.countplot(x='性别',hue='睡眠障碍',data=df,palette='Set3')

plt.title('男女睡眠障碍情况',fontsize=20)

plt.show()plt.figure(figsize=(12,8))

sns.countplot(x='性别',hue='BMI',data=df,palette='Set3')

plt.title('男女BMI情况',fontsize=20)

plt.show()plt.figure(figsize=(12,8))

plt.hist(df['年龄'],density=True,bins=15,color=plt.cm.RdBu(0.6),edgecolor=plt.cm.RdBu(0.7))

df['年龄'].plot(kind = 'kde')

plt.title('年龄分布',fontsize=20)

plt.show()df['年龄'].min(),df['年龄'].max()plt.figure(figsize=(12,8))

plt.hist(df['睡眠时长'],density=True,bins=15,color=plt.cm.RdBu(0.6),edgecolor=plt.cm.RdBu(0.7))

df['睡眠时长'].plot(kind = 'kde')

plt.title('睡眠时间分布',fontsize=20)

plt.show()plt.figure(figsize=(12,8))

plt.hist(df['睡眠质量'],density=True,bins=6,color=plt.cm.RdBu(0.6),edgecolor=plt.cm.RdBu(0.7))

df['睡眠质量'].plot(kind = 'kde')

plt.title('睡眠质量分布',fontsize=20)

plt.show()plt.figure(figsize=(12,8))

plt.hist(df['心率'],density=True,bins=15,color=plt.cm.RdBu(0.6),edgecolor=plt.cm.RdBu(0.7))

df['心率'].plot(kind = 'kde')

plt.title('心率分布',fontsize=20)

plt.show()plt.figure(figsize=(12,8))

plt.hist(df_new['高压'],density=True,bins=15,color=plt.cm.RdBu(0.6),edgecolor=plt.cm.RdBu(0.7),label='高压')

df_new['高压'].plot(kind = 'kde',label='高压')

plt.hist(df_new['低压'],density=True,bins=15,color=plt.cm.RdBu(0.3),edgecolor=plt.cm.RdBu(0.2),label='低压')

df_new['低压'].plot(kind = 'kde',label='低压')

plt.title('血压分布',fontsize=20)

plt.legend()

plt.show()df_new['高压'].max(),df_new['高压'].min(),df_new['低压'].min(),df_new['低压'].max()plt.figure(figsize=(12,8))

plt.hist(df['身体活动水平'],density=True,bins=15,color=plt.cm.RdBu(0.6),edgecolor=plt.cm.RdBu(0.7))

df['身体活动水平'].plot(kind = 'kde')

plt.title('身体活动水平分布',fontsize=20)

plt.show()df['身体活动水平'].min(),df['身体活动水平'].max()plt.figure(figsize=(12,8))

plt.hist(df['压力水平'],density=True,bins=15,color=plt.cm.RdBu(0.6),edgecolor=plt.cm.RdBu(0.7))

df['压力水平'].plot(kind = 'kde')

plt.title('压力水平分布',fontsize=20)

plt.show()plt.figure(figsize=(12,8))

plt.hist(df['每日步数'],density=True,bins=15,color=plt.cm.RdBu(0.6),edgecolor=plt.cm.RdBu(0.7))

df['每日步数'].plot(kind = 'kde')

plt.title('每日步数分布',fontsize=20)

plt.show()sns.pairplot(df_new[df_new.columns.tolist()[1:]])plt.figure(figsize=(12,12))

plt.imshow(df_new.iloc[:,1:].corr(),cmap='Blues')

plt.xticks(range(len(df_new.iloc[:,1:].corr().columns.tolist())),df_new.iloc[:,1:].corr().columns.tolist(),rotation=45)

plt.yticks(range(len(df_new.iloc[:,1:].corr().columns.tolist())),df_new.iloc[:,1:].corr().columns.tolist(),rotation=45)

plt.colorbar()

plt.show()target = ['睡眠时长','睡眠质量','睡眠障碍']

df_new.drop(columns=['ID'],inplace=True)df_new.drop(columns=['血压'],inplace=True)for i in range(len(target[:2])):

    y = df_new[target[i]]

    X = df_new.iloc[:,~df_new.columns.isin(target)]

    model = RandomForestRegressor()

    model.fit(X,y)

    print('在'+ target[i] + '作为因变量时，各因素重要性为：')

    plt.figure(figsize=(8,8))

    plt.subplot(2,1,i+1)

    plt.imshow(model.feature_importances_.reshape(-1,1))

    plt.yticks(range(len(X.columns.tolist())),X.columns.tolist())

    plt.xticks(range(1))

    plt.xlabel(target[i])

    plt.colorbar()

    plt.show()y = df_new[target[2]]

X = df_new.iloc[:,~df_new.columns.isin(target)]

model1 = RandomForestClassifier()

model1.fit(X,y)

plt.imshow(model1.feature_importances_.reshape(-1,1))

plt.yticks(range(len(X.columns.tolist())),X.columns.tolist())

plt.xticks(range(1))

plt.xlabel(target[2])

plt.colorbar()

plt.show()plt.figure(figsize=(4,8))

sns.boxplot(x='性别',y='身体活动水平',palette='Set3',data=df_new)

plt.title('不同性别身体活动水平的箱型图分析',fontsize=15)

plt.show()plt.figure(figsize=(4,8))

sns.boxplot(x='性别',y='压力水平',palette='Set3',data=df_new)

plt.title('不同性别压力水平的箱型图分析',fontsize=15)

plt.show()lt.figure(figsize=(4,8))

sns.boxplot(x='性别',y='心率',palette='Set3',data=df_new)

plt.title('不同性别心率的箱型图分析',fontsize=15)

plt.show()plt.figure(figsize=(12,8))

sns.boxplot(x='性别',y='高压',palette='Set3',data=df_new)

sns.boxplot(x='性别',y='低压',palette='Set3',data=df_new)

plt.title('不同性别血压的箱型图分析',fontsize=15)

plt.show()X = df_new.drop(columns=['睡眠障碍'])

y = df_new[['睡眠障碍']]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, train_size=0.7, random_state=42)model2 = xgboost.XGBClassifier()

model2.fit(X_train, y_train)y_pred = model2.predict(X_test)df_new['睡眠障碍'].unique()cm = confusion_matrix(y_test, y_pred)label_mapping = {0:'失眠',1:'无',2:'睡眠呼吸暂停'}

for i, true_label in enumerate(label_mapping):

    row = ''

    for j, pred_label in enumerate(label_mapping.values()):

        row += f'{cm[i, j]} ({pred_label})\t'

    print(f'{row} | {true_label}')

print(classification_report(y_test, y_pred,target_names=['失眠','无', '睡眠呼吸暂停'])) 

fig, ax = plt.subplots()

im = ax.imshow(cm, interpolation='nearest', cmap=plt.cm.Blues)

ax.figure.colorbar(im, ax=ax)

ax.set(xticks=np.arange(cm.shape[1]),

       yticks=np.arange(cm.shape[0]),

       xticklabels=label_names, yticklabels=label_names,

       title='Confusion matrix',

       ylabel='True label',

       xlabel='Predicted label')

thresh = cm.max() / 2.

for i in range(cm.shape[0]):

    for j in range(cm.shape[1]):

        ax.text(j, i, format(cm[i, j], 'd'),

                ha="center", va="center",

                color="white" if cm[i, j] > thresh else "black")

fig.tight_layout()

plt.show()

网址：python大数据分析 https://www.yuejiaxmz.com/news/view/202831

相关内容

Python数据分析实战
Python数据分析：对饮食与健康数据的分析与可视化
python excel数据分析师职业技能
python数据分析
Python中的生活数据分析与个人健康监测.pptx
生活中的什么数据可以做数据分析
Python数据分析：统计函数绘制简单图形
django+hadoop基于Python的王者荣耀战队的数据分析系统(源码+文档+调试+可视化大屏)
利用Python进行数据分析——Pandas(2)
【Python】Python连接Hadoop数据中遇到的各种坑（汇总）

随便看看