-
Notifications
You must be signed in to change notification settings - Fork 0
/
RandomForestsClassifier.py
71 lines (57 loc) · 2.39 KB
/
RandomForestsClassifier.py
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
# -*- coding: utf-8 -*-
"""
Created on Sat Jul 14 17:39:48 2018
@author: Aditya
"""
# Natural Language Processing
# Importing the libraries
import pandas as pd
# Importing the dataset
dataset = pd.read_csv('Restaurant_Reviews.tsv', delimiter = '\t', quoting = 3)
# Cleaning the texts
import re
#nltk.download('stopwords')
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer
corpus = []
for i in range(0, 1000):
review = re.sub('[^a-zA-Z]', ' ', dataset['Review'][i])
review = review.lower()
review = review.split()
ps = PorterStemmer()
review = [ps.stem(word) for word in review if not word in set(stopwords.words('english'))]
review = ' '.join(review)
corpus.append(review)
# Creating the Bag of Words model
from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer(max_features = 1500)
X = cv.fit_transform(corpus).toarray()
y = dataset.iloc[:, 1].values
# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20, random_state = 17)
# Fitting Random Forest Classification to the Training set
from sklearn.ensemble import RandomForestClassifier
classifier = RandomForestClassifier(n_estimators = 73, criterion = 'entropy', random_state = 0)
classifier.fit(X_train, y_train)
# Predicting the Test set results
y_pred = classifier.predict(X_test)
#k cross validation
from sklearn.model_selection import cross_val_score
accuracies = cross_val_score(estimator = classifier, X = X_train, y = y_train, cv = 10)
print(accuracies.mean())
print(accuracies.std())
#confusion matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
# Applying Grid Search to find the best model and the best parameters
from sklearn.model_selection import GridSearchCV
parameters = [{'criterion': ['entropy'], 'n_estimators': [65,66,67,68,69,70,71,72,73,74,75,76,77,78,79]}]
grid_search = GridSearchCV(estimator = classifier,
param_grid = parameters,
scoring = 'accuracy',
cv = 10,
n_jobs = -1)
grid_search = grid_search.fit(X_train, y_train)
print('best_accuracy = ',grid_search.best_score_)
print('best_parameters = ',grid_search.best_params_)