基于逻辑回归的分类预测鸢尾花分类

Task01：基于逻辑回归的分类预测

鸢尾花分类

# -*- coding: utf-8 -*-
"""
Created on Mon Jun 22 10:32:41 2020

@author: asus
"""

import pandas as pd
from pandas.plotting import scatter_matrix
from matplotlib import pyplot
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import StratifiedKFold
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
dataset =pd.read_csv(r"C:/Users/asus/Desktop/testhomework/iris dataset.csv",engine='python',encoding="utf_8_sig")
names = ['sepal-length', 'sepal-width', 'petal-length', 'petal-width', 'class']
# print(dataset.shape)
# #检查数据类型
# print(dataset.head(20))
# #检查前20行数据
# print(dataset.describe())
# #利用describe函数进行统计摘要
dataset.plot(kind='box', subplots=True, layout=(2,2), sharex=False, sharey=False)
pyplot.show()
#得到各特征属性分布
dataset.hist()
pyplot.show()
#每个变量创建直方图
scatter_matrix(dataset)
pyplot.show()
#变量之间的相互作用
import matplotlib.pyplot as plt
plt.style.use('ggplot')

array = dataset.values
X = array[:,0:4]
y = array[:,4]
X_train, X_validation, Y_train, Y_validation = train_test_split(X, y, test_size=0.30, random_state=1)
#将数据分片 形成训练集70%测试集30%
model = SVC(gamma='auto')
model.fit(X_train, Y_train)
predictions = model.predict(X_validation)
#使用支持向量机拟合模型进行训练
print(accuracy_score(Y_validation, predictions))
print(confusion_matrix(Y_validation, predictions))
print(classification_report(Y_validation, predictions))
#可以得到预测值在97%