gaganmanku96

import os
from tqdm import tqdm
import pandas as pd
import numpy as np
import re

from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score
from sklearn.utils import shuffle
from sklearn.linear_model import LogisticRegression

gaganmanku96

import os
from tqdm import tqdm
import pandas as pd
import numpy as np
import re

from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score
from sklearn.utils import shuffle
from sklearn.linear_model import LogisticRegression

gaganmanku96

class LabeledLineSentence():
    def __init__(self,fileName):
        self.fileName = fileName
        
    def __iter__(self):
        df = pd.read_csv(self.fileName)
        text = df['text'].values
        for idx, doc in tqdm(enumerate(text)):
            doc = self.preprocess(doc)
            yield TaggedDocument(words=doc.split(),tags=[idx])

gaganmanku96

iterator = LabeledLineSentence('..')
model = Doc2Vec(iterator,min_count=1, vector_size=250, sample=1e-4, negative=6 ,workers=4,epochs=2)

gaganmanku96

model.train(iterator, total_examples=model.corpus_count, epochs=5)

gaganmanku96

model.wv.most_similar('wine')

gaganmanku96

model.wv.most_similar('wine')

gaganmanku96

model.wv.most_similar('food')

gaganmanku96

rating = []
df = pd.read_csv('..')
rating = df['target'].values
del df
'''
These values are determined by len of your dataset. If you have 25k as length then you can use 20k for training and 5k for testing.
'''
train_arrays = np.ones((20000, 250))
train_labels = np.ones(20000,dtype='int')
test_arrays = np.zeros((5000, 250))

gaganmanku96

classifier = LogisticRegression(solver='lbfgs',C=0.5)
classifier.fit(train_arrays,train_labels)
pred = classifier.predict(test_arrays)
'''
You can check the accuracy of model using sklearn's confusion matrix or accuracy_score function.
'''