数据标准化+网格搜索+交叉验证+预测（Python）

Download datasets iris_training.csv from: https://github.com/tensorflow/tensorflow/tree/master/tensorflow/examples/tutorials/monitors

Method: SVR

# -*- coding: utf-8 -*-

import pandas as pd
from sklearn.grid_search import GridSearchCV
from sklearn import svm, datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.utils import shuffle
import numpy as np
from sklearn import metrics
df = pd.read_csv('iris_training.csv', header=0)
parameters = {'kernel':['rbf'], 'gamma':np.logspace(-5, 0, num=6, base=2.0),'C':np.logspace(-5, 5, num=11, base=2.0)}
grid_search = GridSearchCV(svm.SVR(), parameters, cv=10, n_jobs=4, scoring='mean_squared_error')

X = df[df.columns.drop('virginica')]
y = df['virginica']

X_train, X_test, y_train, y_test = train_test_split(\
    X, y, test_size=0.3, random_state=42)

random_seed = 13
X_train, y_train = shuffle(X_train, y_train, random_state=random_seed)
X_scaler = StandardScaler()
X_train = X_scaler.fit_transform(X_train)
X_test = X_scaler.transform(X_test)

grid_search.fit(X_train,y_train)
y_pred = grid_search.predict(X_test) 

print 'mean_squared_error:'+str(metrics.mean_squared_error(y_test,y_pred)),\
 'r2_score:'+str(metrics.r2_score(y_test,y_pred))

 

Neural Network:

# -*- coding: utf-8 -*-

import pandas as pd
from sklearn.grid_search import GridSearchCV
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.utils import shuffle
import numpy as np
from sklearn import metrics
from sklearn.neural_network import MLPRegressor
df = pd.read_csv('iris_training.csv', header=0)

#neural networks for regresion
parameters = {'hidden_layer_sizes':[200,250,300,400,500,600], 'activation':['relu']}
grid_search = GridSearchCV(MLPRegressor(), parameters, cv=10, n_jobs=4, scoring='mean_squared_error')

X = df[df.columns.drop('virginica')]
y = df['virginica']

X_train, X_test, y_train, y_test = train_test_split(\
	X, y, test_size=0.3, random_state=42)

random_seed = 13
X_train, y_train = shuffle(X_train, y_train, random_state=random_seed)
X_scaler = StandardScaler()
X_train = X_scaler.fit_transform(X_train)
X_test = X_scaler.transform(X_test)

grid_search.fit(X_train,y_train)
y_pred = grid_search.predict(X_test) 

print 'mean_squared_error:'+str(metrics.mean_squared_error(y_test,y_pred)),\
 'r2_score:'+str(metrics.r2_score(y_test,y_pred))