kaggle入窝－

#!/usr/bin/env python
# coding: utf-8

# # sklearn常用方法

# # #标准化　（需要使用距离来度量相似性或用ＰＣＡ降维时）

# In[1]:


from sklearn.preprocessing import StandardScaler
data_train = StandardScaler().fit_transform(data_train)
data_test = StandardScaler().fit_transform(data_test)


# In[ ]:


from sklearn.preprocessing import MinMaxScaler
data = MinMaxScaler().fit_transform(data)


# In[ ]:


from sklearn.preprocessing import Normalizer
data = Normalizer().fit_transform(data)


# In[ ]:


from sklearn.preprocessing import Binarizer
data = Binarizer(threshold=epsilon).fit_transform(data)


# # #　类别型特征转换为数值型特征：保留数值型特征，并将不同的类别转换为读热编码

# In[ ]:


from sklearn.feature_extraction import DictVectorizer
vec = DictVectorizer(sparse=False)
X_train = vec.fit_transform(X_train.to_dict(orient='recoed'))


# # 卡方检验

# In[ ]:


from sklearn.feature_extraction import selectKBest
from sklearn.feature_extraction import chi2
# 选择Ｋ个最好的特征，返回选择特征后的数据
skb = SelectKBest(chi2, k=10).fit(X_train, Y_train)
X_train = skb.transform(X_train)
X_test = skb.transform(X_test)


# # 互信息法

# In[2]:


from sklearn.feature_extraction import SelectKBest
from minepy import MINE
# 由于ＭＩＮＥ的设计不是函数式的，定义mic的方法将其设为函数式的，返回一个二元组，二元组的第２项设置成固定的Ｐ值０．５
def mic(x, y):
    m = MINE()
    m.compute_score(x, y)
    return(m.mic(), 0.5)
# 选择Ｋ个最好的特征，返回选择特征后的数据
SelectKBest(lambda X, Y: array(map(lambda x:mic(x, Y), X.T)).T, k=2).fit_transform(iris.data, iris.taget)


# In[ ]:


from sklearn.decomposition import PCA
estimator = PCA(n_components=2)
X_pca = estimator.fit_transform(X_data)


# # 开始算法

# In[ ]:


from sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.25, random_state=7)


# In[ ]:


from sklearn.XXXXXXX import AlgorithmXXX
alg = AlgorithmXXX()
alg.fit(X_train, Y_train)
y_predict = alg.predict(x_test)


# In[ ]:


from sklearn.linear_model import SGDClassifier
sgd = SGDClassifier()


# In[ ]:


from sklearn.linear_model import SGDRegressor
sgd = SGDRegressor(loss='squared_loss', penalty=None, random_state=7)


# In[ ]:


from sklearn.svm import SVR
svr = SVR(kernel='linear')# linear/poly/ rbf


# In[ ]:


from sklearn.svm import SVC
svc = SVC(kernel='linear')


# In[ ]:


from sklearn.naive_bayes import MultinomialNB
mnb = MultinomialNB()


# In[ ]:


from sklearn.tree import DecisionTreeClassifier
dtc = DecisionTreeClassifier(criterion='entropy', max_depth=3, min_samples_leaf=5)# 最大深度与最小样本数，防止过拟合


# In[ ]:


from sklearn.ensemble import RandomForestClassifier
rfc = RandomForestClassifier(max_depth=3, min_samples_leaf=5)


# In[ ]:


from sklearn.ensemble import GradientBoostingClassifier
gbc = GradientBoostingClassifier(max_depth=3, min_samples_leaf=5)


# In[ ]:


from sklearn.ensemble import ExtraTreesClassifier
etr = ExtraTreesClassifier()


# In[ ]:


from sklearn import metrics
accuracy_rate = metrics.accuracy_score(y_test, y_predict)
metrics.classification_report(y_test, y_predict, target_names=data.target_names)


# In[ ]:


from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
kfold = KFold(n_splits=10, random_state=7)
result = cross_val_score(model, X, Y, cv=kfold)