Python Machine Learning

from sklearn import datasets
    iris = datasets.load_iris()

from sklearn.cross_validation import train_test_split
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)


from sklearn.linear_model import Perceptron
    ppn = Perceptron(n_iter=40, eta0=0.1, random_state=0)
    ppn.fit(X_train_std, y_train)
    y_pred = ppn.predict(X_test_std)

from sklearn.metrics import accuracy_score
    accuracy_score(y_test, y_pred)

from sklearn.linear_model import LogisticRegression
    lr = LogisticRegression(C=1000.0, random_state=0)
    lr.fit(X_train_std, y_train)
    lr.predict_proba(X_test_std[0, :])

from sklearn.svm import SVC
    svm = SVC(kernel='linear', C=1.0, random_state=0)
    svm.fit(X_train_std, y_train)
    svm = SVC(kernel='rbf', random_state=0, gamma=0.10, C=10.0)
    svm.fit(X_xor, y_xor)

from sklearn.linear_model import SGDClassifier
    ppn = SGDClassifier(loss='perceptron')
    lr = SGDClassifier(loss='log')
    svm = SGDClassifier(loss='hinge')

from sklearn.preprocessing import Imputer
    imr = Imputer(missing_values='NaN', strategy='mean', axis=0)
    imr = imr.fit(df)
    imputed_data = imr.transform(df.values)

from sklearn.preprocessing import LabelEncoder
    class_le = LabelEncoder()
    y = class_le.fit_transform(df['classlabel'].values)
    y = class_le.inverse_transform(y)

from sklearn.preprocessing import OneHotEncoder
    ohe = OneHotEncoder(categorical_features=[0])
    ohe.fit_transform(X).toarray()
    pd.get_dummies(df[['price', 'color', 'size']])

from sklearn.preprocessing import MinMaxScaler
    mms = MinMaxScaler()
    X_train_norm = mms.fit_transform(X_train)
    X_test_norm = mms.transform(X_test)

from sklearn.preprocessing import StandardScaler
    sc = StandardScaler()
    sc.fit(X_train)
    X_train_std = sc.transform(X_train)
    X_test_std = sc.transform(X_test)

from sklearn.preprocessing import StandardScaler
    stdsc = StandardScaler()
    X_train_std = stdsc.fit_transform(X_train)
    X_test_std = stdsc.transform(X_test)

from sklearn.linear_model import LogisticRegression
    LogisticRegression(penalty='l1')

    lr = LogisticRegression(penalty='l1', C=0.1)
    lr.fit(X_train_std, y_train)
    lr.score(X_train_std, y_train)
    lr.score(X_test_std, y_test)

    lr.intercept_
    lr.coef_

from sklearn import tree
    target = train["Survived"].values
    features = train[["Sex", "Age"]].values
    my_tree = tree.DecisionTreeClassifier()
    my_tree = my_tree.fit(features, target)

from sklearn.ensemble import RandomForestClassifier