数据分析--模型建立和评估

数据分析–模型建立和评估

---

---

一、模型搭建

1.1导入数据集

import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from IPython.display import Image
%matplotlib inline
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号
plt.rcParams['figure.figsize'] = (10, 6)  # 设置输出图片大小
# 读取训练数集
train = pd.read_csv('train.csv')
train.head()

PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S

1.2读取清洗过的数据集

data = pd.read_csv('clear_data.csv')
data.head()

PassengerId	Pclass	Age	SibSp	Parch	Fare	Sex_female	Sex_male	Embarked_C	Embarked_Q	Embarked_S
0	0	3	22.0	1	0	7.2500	0	1	0	0	1
1	1	1	38.0	1	0	71.2833	1	0	1	0	0
2	2	3	26.0	0	0	7.9250	1	0	0	0	1
3	3	1	35.0	1	0	53.1000	1	0	0	0	1
4	4	3	35.0	0	0	8.0500	0	1	0	0	1

1.3切割训练集和测试集

from sklearn.model_selection import train_test_split
X = data
y = train['Survived']
X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=0)
X_train.shape, X_test.shape

((668, 11), (223, 11))

1.4模型创建

from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
lr = LogisticRegression()
lr.fit(X_train, y_train)

print("Training set score: {:.2f}".format(lr.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(lr.score(X_test, y_test)))

Training set score: 0.80
Testing set score: 0.79

调整参数后的逻辑回归模型

lr2 = LogisticRegression(C=100)
lr2.fit(X_train, y_train)
print("Training set score: {:.2f}".format(lr2.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(lr2.score(X_test, y_test)))

Training set score: 0.79
Testing set score: 0.78

1.5输出模型预测结果

pred = lr.predict(X_train)
pred_proba = lr.predict_proba(X_train)
pred_proba[:10]

array([[0.60870022, 0.39129978],
       [0.17725433, 0.82274567],
       [0.40750365, 0.59249635],
       [0.18925851, 0.81074149],
       [0.87973912, 0.12026088],
       [0.91374559, 0.08625441],
       [0.13293198, 0.86706802],
       [0.90560801, 0.09439199],
       [0.05283987, 0.94716013],
       [0.10936016, 0.89063984]])

二、模型评估

2.1引入库

import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from IPython.display import Image
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
%matplotlib inline
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号
plt.rcParams['figure.figsize'] = (10, 6)  # 设置输出图片大小
from sklearn.model_selection import train_test_split
data = pd.read_csv('clear_data.csv')
train = pd.read_csv('train.csv')
X = data
y = train['Survived']
X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=0)
lr = LogisticRegression()
lr.fit(X_train, y_train)

2.2交叉验证

from sklearn.model_selection import cross_val_score
lr = LogisticRegression(C=100)
scores = cross_val_score(lr, X_train, y_train, cv=10)
print("Average cross-validation score: {:.2f}".format(scores.mean()))

Average cross-validation score: 0.80

2.3混淆矩阵

from sklearn.metrics import confusion_matrix
lr = LogisticRegression(C=100)
lr.fit(X_train, y_train)
pred = lr.predict(X_train)
confusion_matrix(y_train, pred)
from sklearn.metrics import classification_report
print(classification_report(y_train, pred))

precision    recall  f1-score   support

           0       0.81      0.86      0.83       412
           1       0.75      0.68      0.71       256

    accuracy                           0.79       668
   macro avg       0.78      0.77      0.77       668
weighted avg       0.79      0.79      0.79       668

---