[人工智能]机器学习初步模型

1、回归：

? ? ? ? ? ? ? ? 假设已经认为该数据为三次方数据：

import statsmodels.api as sm
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np

nsample = 100
#x的取值
x = np.linspace(0, 10, nsample)
#列出x的列的组成
X = np.column_stack((x, x**2,x**3))

#给x加上一个常数
X = sm.add_constant(X)
#模拟方程的系数
beta = np.array([1,0.1,10,1])
#误差
e = np.random.normal(size=nsample)
#生成Y的等式
y = np.dot(X, beta) + e
##调用OLS。fit来拟合曲线
model = sm.OLS(y,X).fit()


fig, ax = plt.subplots(figsize=(8,6))
ax.plot(x, y, label='data')
ax.legend(loc='best')
ax.scatter(x,y)
plt.show()

?2、分类

在iris数据集上来进行分类器分类

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.datasets import load_iris

iris = load_iris()
##x为数据集
x = iris["data"]
##y为标签集
y = iris["target"]
##打破原有的顺序进行分割,分为x的训练集、测试集；y的训练集、测试集
xtrain,xtest,ytrain,ytest = train_test_split(x,y,test_size=0.3,random_state=0)

########随机森林
##定义一个分类器
rfc = RandomForestClassifier(max_depth=5,random_state=0)
rfc.fit(xtrain,ytrain)  ##将训练集的数据进行拟合
y_pred = rfc.predict(xtest)   #求出预测的值

########
gtc = GradientBoostingClassifier(max_depth=5,random_state=0)
gtc.fit(xtrain,ytrain)
gtc_pred = gtc.predict(xtest)

########
########
hbc = HistGradientBoostingClassifier(max_depth=5,random_state=0)
hbc.fit(xtrain,ytrain)
hbc_pred = hbc.predict(xtest)

##随机森林
rf = pd.DataFrame(list(zip(ytest,y_pred)),columns=['real','pred'])
rf["num"] = rf.apply(lambda r:1 if r["real"] == r["pred"] else 0,axis=1)
#####验证准确率
print(sum(rf["num"])/len(rf["real"]))

##
gtcf = pd.DataFrame(list(zip(ytest,gtc_pred)),columns=['real','pred'])
gtcf["num"] = rf.apply(lambda r:1 if r["real"] == r["pred"] else 0,axis=1)
print(sum(gtcf["num"])/len(gtcf["real"]))




#####增加学习率的

from sklearn.ensemble import RandomForestClassifier
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split

iris = load_iris()
x = iris["data"]
y = iris["target"]

x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.3,random_state=0)

for i in range(40):
    clf = RandomForestClassifier(max_depth=5,n_estimators=i+1)
    clf.fit(x_train,y_train)
    pred = clf.predict(x_test)
    rf = pd.DataFrame(list(zip(y_test,pred)),columns=["test","pred"])
    rf["num"] = rf.apply(lambda r:1 if r["test"] == r["pred"] else 0,axis=1)
    print(sum(rf["num"])/len(rf["test"]))
    plt.scatter(i,sum(rf["num"])/len(rf["test"]))
plt.show()

0.9777777777777777
0.9777777777777777

关注博主即可阅读全文