Machine-Learning-Text-Classification/Classification.py at main · Ariffkmy/Machine-Learning-Text-Classification · 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
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159

# coding: utf-8

# In[2]:

import pandas as pd

from sklearn import model_selection, preprocessing, linear_model, naive_bayes, metrics, svm
from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from sklearn import decomposition, ensemble

import pandas,  numpy, string
# from keras.preprocessing import text, sequence
# from keras import layers, models, optimizers


# In[3]:

# from flask import Flask , request
# from flask_restplus import Api , Resource , fields
# from flask_cors import CORS, cross_origin
# from waitress import serve


# In[ ]:


# In[ ]:


# In[4]:

df=pd.read_excel('AI Dataset.xlsx')


# In[5]:

# df.head()


# In[6]:

# df['TAG'].unique()


# In[7]:

# df[df['TAG']=='Negative MPU4 Committee Feedback'].shape


# In[8]:

# len(df['TAG'].unique())


# In[9]:

train_x, valid_x, train_y, valid_y = model_selection.train_test_split(df['COMMENT'], df['TAG'])


# In[ ]:


# In[10]:

# word level tf-idf
tfidf_vect = TfidfVectorizer(analyzer='word', token_pattern=r'\w{1,}', max_features=5000)

tfidf_vect.fit(df['COMMENT'].values.astype('U'))
xtrain_tfidf =  tfidf_vect.transform(train_x.values.astype('U'))
xvalid_tfidf =  tfidf_vect.transform(valid_x.values.astype('U'))


# In[ ]:


# In[11]:


# Linear Classifier on Word Level TF IDF Vectors
# accuracy = train_model(linear_model.LogisticRegression(), xtrain_tfidf, train_y, xvalid_tfidf)
# print("LR, WordLevel TF-IDF: ", accuracy)


# In[12]:


classifier=linear_model.LogisticRegression()
# fit the training dataset on the classifier
classifier.fit(xtrain_tfidf, train_y)
# predict the labels on validation dataset


# In[13]:

def testaRecord(str_record):
    xvalid_tfidf =  tfidf_vect.transform([str_record])
    predictions = classifier.predict(xvalid_tfidf)
    return predictions


# In[14]:

# testaRecord('you are good')


# In[15]:

# xvalid_tfidf =  tfidf_vect.transform(["MPU4 Committee"])


# In[16]:

# result=pd.DataFrame(columns=['Name','StudentID','Email','ProjectTitle','Feedback','Tag'])


# In[17]:

def Call_function(name_,studentid_,email_,ptitle_,feedback_):
    result=pd.read_excel('Results.xlsx')
    tag=testaRecord(feedback_)[0]
    tmp_=pd.DataFrame(columns=['Name','StudentID','Email','ProjectTitle','Feedback','Tag'],data=[[name_,studentid_,email_,ptitle_,feedback_,tag]])
    result=pd.concat([result,tmp_])
    result.to_excel('Results.xlsx')

    return tag


# In[18]:

# Call_function("Ariff","MSDS17046","asd@adsf.com","Idk","THis was a good project")


# In[20]:

# Call_function("Ariff","MSDS17046","asd@adsf.com","Idk","THis was a good project")


# In[ ]:


# In[ ]:


# In[ ]: