python之sklearn学习

# -*- coding: utf-8 -*-
import numpy as np
from sklearn import metrics
import csv

def readArray(file):  # 读取文件
    Data = []
    reader = csv.reader(open(file), delimiter=',', quotechar='\'')

    for row in reader:
        row = [float(x) for x in row]
        Data.append(row)

    Data = np.array(Data)
    return Data

def report():  # 输出结果

    report = metrics.classification_report(y_test, y_predict)
    m = metrics.confusion_matrix(y_test, y_predict)
    print(report)
    print(m)
    
print("Start")
train_path_X = "X_train_breast_cancer.csv"
train_path_y = "y_train_breast_cancer.csv"
X = readArray(train_path_X)
y = readArray(train_path_y)
y = y.ravel()

print("Ada Data OK")

#### 训练
"""
# 逻辑回归
from sklearn.ensemble import AdaBoostClassifier
model = AdaBoostClassifier()
model.fit(X, y)  # 模型训练
"""
"""
# 决策树
from sklearn.datasets import load_iris
from sklearn import tree
iris = load_iris()
model = tree.DecisionTreeClassifier()
model.fit(X, y)  # 模型训练
"""
"""
# 贝叶斯方法
from sklearn.naive_bayes import GaussianNB
model = GaussianNB()
model.fit(X, y)
"""
"""
# KNN方法
from sklearn import neighbors,datasets
model = neighbors.KNeighborsClassifier()
model.fit(X,y)
"""
"""
# LR方法
from sklearn.linear_model import LogisticRegression
model = LogisticRegression()
model.fit(X,y)
"""

# MLP方法
from sklearn.neural_network import MLPClassifier
model = MLPClassifier()
model.fit(X,y)

###### 预测
predict_path_X = "X_test_breast_cancer.csv"
predict_path_y = "y_test_breast_cancer.csv"

X_test = readArray(predict_path_X)
y_test = readArray(predict_path_y)

print("predict...")
y_predict = model.predict(X_test)  # 模型测试


report()

print("Done!!!!!!")