python1/phuong.py at master · tamcb2708/python1 · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87

import os

import matplotlib.pyplot as plt
import pandas as pd
from sklearn import linear_model
from sklearn.linear_model import Ridge
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import PolynomialFeatures

def get_home_data():
    """Get home data, from local csv."""
    if os.path.exists("data/iris.csv"):
        print("-- iris.csv found locally")
        df = pd.read_csv("data/iris.csv")

    return df


def plotting_features_vs_target(features, x, y):
    # define number of subplot
    num_feature = len(features)
    f, axes = plt.subplots(1, num_feature, sharey=True)

    # plotting
    for i in range(0, num_feature):
        axes[i].scatter(x[features[i]], y)
        axes[i].set_title(features[i])

    plt.show()


if __name__ == "__main__":
    df = get_home_data()
    # features selection
    features = list(["Species", "PetalLengthCm"])
    print("Features name:", list(df.columns.values))
    print("Selected features:", features)
    y = df["Id"]
    X = df[features]

    x_train, x_test, y_train, y_test = train_test_split(X, y)


    plotting_features_vs_target(features, x_train, y_train)


    # training model
    linear = linear_model.LinearRegression()
    linear.fit(x_train, y_train)

    # evaluating model
    score_trained = linear.score(x_test, y_test)
    print ("Model scored:", score_trained)


    # L1 regularization
    lasso_linear = linear_model.Lasso(alpha=1.0)
    lasso_linear.fit(x_train, y_train)

    # evaluating L1 regularized model
    score_lasso_trained = lasso_linear.score(x_test, y_test)
    print ("Lasso model scored:", score_lasso_trained)


    # L2 regularization
    ridge_linear = Ridge(alpha=1.0)
    ridge_linear.fit(x_train, y_train)

    # evaluating L2 regularized model
    score_ridge_trained = ridge_linear.score(x_test, y_test)
    print ("Ridge model scored:", score_ridge_trained)


    poly_model = Pipeline([('poly', PolynomialFeatures(degree=2)),
                           ('linear', linear_model.LinearRegression(fit_intercept=False))])
    poly_model = poly_model.fit(x_train, y_train)
    score_poly_trained = poly_model.score(x_test, y_test)
    print ("Poly model scored:", score_poly_trained)

    poly_model = Pipeline([('poly', PolynomialFeatures(interaction_only=True, degree=2)),
                           ('linear', linear_model.LinearRegression(fit_intercept=False))])
    poly_model = poly_model.fit(x_train, y_train)
    score_poly_trained = poly_model.score(x_test, y_test)
    print ("Poly model (interaction only) scored:", score_poly_trained)