Last active
December 23, 2019 07:04
-
-
Save puraminy/f1b1a19765b143ac27249ab369e4f1d7 to your computer and use it in GitHub Desktop.
Forward Feature Selection in Machine Learning
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
import pandas as pd | |
from sklearn.metrics import confusion_matrix | |
from sklearn.metrics import accuracy_score | |
from sklearn import preprocessing | |
from sklearn.neighbors import KNeighborsClassifier | |
from sklearn.neighbors import RadiusNeighborsClassifier | |
from sklearn.naive_bayes import GaussianNB | |
import matplotlib.pyplot as plt | |
x_train = pd.read_csv('Train_Data.csv') | |
y_train = pd.read_csv('Train_Labels.csv') | |
x_test = pd.read_csv('Test_Data.csv') | |
y_test = pd.read_csv('Test_Labels.csv') | |
print(x_train.shape) | |
x_train.shape | |
r = -1 | |
x_train = x_train.iloc[:r] | |
y_train = y_train.iloc[:r] | |
x_test = x_test.iloc[:r] | |
y_test = y_test.iloc[:r] | |
def preprocess(data): | |
# in this part we scale data between [0.1] | |
min_max_scaler = preprocessing.MinMaxScaler() | |
x_train_minmax = min_max_scaler.fit_transform(data) | |
return x_train_minmax | |
x_train = preprocess(x_train) | |
x_test = preprocess(x_test) | |
def forward_selection(data, response, classifier, alpha=0.01, exclude=[]): | |
# Specify the columns that you want to exclude from your model | |
cols = data.shape[1] | |
old_acc = 0 | |
sel_cols = [] | |
diff = 1000 | |
acc_list = [] | |
while (diff > alpha): | |
max_acc = 0 | |
selected_col = None | |
for col in range(cols): | |
if (not col in exclude): | |
# print(col, end=" ") | |
x_train_selcols = data[:,sel_cols + [col]] | |
x_test_selcols = x_test[:,sel_cols + [col]] | |
classifier.fit(x_train_selcols, response) | |
y_pred = classifier.predict(x_test_selcols) | |
acc = accuracy_score(y_test, y_pred).round(4) | |
if (acc > max_acc): | |
# print((col,acc)) | |
max_acc = acc | |
selected_col = col | |
diff = max_acc - old_acc | |
# print("max_acc, old_acc, diff", (max_acc, old_acc, diff)) | |
exclude.append(selected_col) | |
if (diff > alpha): | |
sel_cols.append(selected_col) | |
print("{: <80} acc: {}".format('{}'.format(sel_cols), max_acc)) | |
acc_list.append(max_acc) | |
old_acc = max_acc | |
else: | |
print("\n==> No feature to add (based on the difference treshold of alpha:", alpha, ")\n") | |
return sel_cols, acc_list | |
# import warnings | |
# warnings.filterwarnings('ignore') | |
from sklearn.neighbors import KNeighborsClassifier | |
naive_bayes = GaussianNB() | |
sel_cols, acc_list = forward_selection(x_train, y_train, naive_bayes, alpha=0.001) | |
print("selected features:", sel_cols, "final acc:", acc_list[-1]) | |
fig = plt.figure(figsize=(10,8)) | |
plt.plot(acc_list) | |
plt.savefig('plot.png') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment