```python
import numpy as np
import pandas as pd
#数据获取 csv , dict,list
from sklearn.model_selection import train_test_split
read_csv(r'C:\Users\Alice\Desktop\Python1\housing.csv'
names=('F_W','F_H','P_H','T')
dict={'Iris-setosa':0,'Iris-versicolor':1,'Iris-virginca':2}
def cvt(t):
return dict[t]
iris_df=pd.r2ead_csv(f,header=None,names=names,converters={4:cvt})
print(iris_df.head(3))
print(iris_df.info())
print(iris_df.describe()) #描述性统
# 加载 converters map ,
#SQL
#Iris-versicolor Iris-setosa Iris-virginica
iris_df['T1']=iris_df['T'].map(dict) #for(Iris-setosa)
print(iris_df.head(2))
print(iris_df['T1'].value_counts())
#2.数据探索-技术 matplotlib ,pandas
import matplotlib.pyplot as plt
import seaborn as sns
plt.figure(figsize=(10,7))
i=0
for col in iris_df.columns:
plt.subplot(2,3,i+1)
plt.hist(iris_df[col])
i=i+1
plt.show()
#3.拆分数据集 split
#train 训练集 test 测试集 ---》用测试集来评估
y=iris_df['T']
X=iris_df[['F_W','F_H','P_W','P_H']]
x_train,x_test,y_train,y_test=train_test_split(X,y,test_size=.2,random_state=21)
#4.建立模型
from sklearn.linear_model import LogisticRegression
lr=LogisticRegression()
lr.fit(x_train,y_train) #
#5.评估模型 scoring --
print(lr.score(x_test,y_test))
```
你读取csv文件的时候缺了一个右括号