File size: 6,702 Bytes
575adcc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56d18f3
575adcc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
import streamlit as st
import pandas as pd
import streamlit.components.v1 as stc
import docx2txt

# NLP Package-used for text analysis
import nltk
from nltk.tokenize import word_tokenize
from nltk.tag import pos_tag
from nltk.stem import WordNetLemmatizer
from nltk.corpus import stopwords
# from nltk import ne_chunk
from nltk.tag import StanfordNERTagger

from collections import Counter

from textblob import TextBlob
import seaborn as sns
import matplotlib.pyplot as plt

from wordcloud import WordCloud

import base64
import time
from app_utils import *

HTML_BANNER = """
    <div style="background-color:green;padding:10px;border-radius:10px">
    <h1 style="color:white;text-align:center;">Text Analysis App </h1>
    </div>
    """

def text_analysis():
    stc.html(HTML_BANNER)
    menu=['Text-analysis','Upload_Files']
    
    choice=st.sidebar.selectbox('Menu',menu)
    if choice=='Text-analysis':
        st.subheader('Analyse Text')
        text=st.text_area("Enter the text to anlayze")
        if (st.button("Analyze")):
            st.success("Success")
            with st.expander('Original Text'):
                st.write(text)
            with st.expander('Text Analysis'):
                token_analysis=nlp_analysis(text)
                st.dataframe(token_analysis)
            with st.expander('Entitites'):
                entity_result=find_entities(text)
                stc.html(entity_result, height=100, scrolling=True)
            
            col1,col2=st.columns(2)

            with col1:

                with st.expander("Word Stats"):
                    st.info("Word Statistics")
                    docx = nt.TextFrame(text)
                    st.write(docx.word_stats())

                with st.expander("Top keywords"):
                    keywords=get_most_common_tokens(text)
                    st.write(keywords)

                with st.expander('Tagged Keywords'):
                    data= pos_tag(word_tokenize(text))
                    st.dataframe(data)
                    visualize_tags=tag_visualize(data)
                    stc.html(visualize_tags,scrolling=True)


                with st.expander("Sentiment"):
                    sent_result=get_semantics(text)
                    st.write(sent_result)

            with col2:

                with st.expander("Plot word freq"):
                    try:
                          fig, ax = plt.subplots()
                          most_common_tokens = dict(token_analysis["Token"].value_counts())
                          sns.countplot(data=token_analysis[token_analysis["Token"].isin(most_common_tokens)], x="Token", ax=ax)
                          ax.set_xlabel('PoS')
                          ax.set_ylabel('Frequency')
                          ax.tick_params(axis='x' , rotation=45)
                          st.pyplot(fig)
                    except:
                        st.warning('Insufficient data')

                with st.expander("Plot part of speech"):
                      try:
                          fig, ax = plt.subplots()
                          most_common_tokens = dict(token_analysis["Position"].value_counts())
                          sns.countplot(data=token_analysis[token_analysis["Position"].isin(most_common_tokens)], x="Position", ax=ax)
                          ax.set_xlabel('PoS')
                          ax.set_ylabel('Frequency')
                          ax.tick_params(axis='x' , rotation=45)
                          st.pyplot(fig)
                      except:
                          st.warning('Insufficient data')
                   
                with st.expander("Plot word cloud"):
                    try:
                        plot_wordcloud(text)
                    except:
                        st.warning('Insufficient data')

            
            with st.expander('Download Results'):
                file_download(token_analysis)






    elif choice == 'Upload_Files':
        text_file = st.file_uploader('Upload Files', type=['docx'])
        if text_file is not None:
            if text_file.type == 'text/plain':
                text = str(text_file.read(), "utf-8")
            else:
                text = docx2txt.process(text_file)

            if (st.button("Analyze")):
                with st.expander('Original Text'):
                    st.write(text)
                with st.expander('Text Analysis'):
                    token_analysis = nlp_analysis(text)
                    st.dataframe(token_analysis)
                with st.expander('Entities'):
                    entity_result = find_entities(text)
                    stc.html(entity_result, height=100, scrolling=True)

                col1, col2 = st.columns(2)

                with col1:
                    with st.expander("Word Stats"):
                        st.info("Word Statistics")
                        docx = nt.TextFrame(text)
                        st.write(docx.word_stats())

                    with st.expander("Top keywords"):
                        keywords = get_most_common_tokens(text)
                        st.write(keywords)

                    with st.expander("Sentiment"):
                        sent_result = get_semantics(text)
                        st.write(sent_result)

                with col2:
                    with st.expander("Plot word freq"):
                        fig, ax = plt.subplots()
                        num_tokens = 10  # Adjust the number of tokens to display as desired
                        most_common_tokens = dict(token_analysis["Token"].value_counts().head(num_tokens))
                        sns.countplot(data=token_analysis[token_analysis["Token"].isin(most_common_tokens)], x="Token", ax=ax)
                        ax.set_xlabel('Token')
                        ax.set_ylabel('Frequency')
                        ax.tick_params(axis='x', rotation=45)
                        st.pyplot(fig)

                    with st.expander("Plot part of speech"):
                        fig, ax = plt.subplots()
                        most_common_tokens = dict(token_analysis["Position"].value_counts())
                        sns.countplot(data=token_analysis[token_analysis["Position"].isin(most_common_tokens)], x="Position", ax=ax)
                        ax.set_xlabel('PoS')
                        ax.set_ylabel('Frequency')
                        ax.tick_params(axis='x', rotation=45)
                        st.pyplot(fig)

                    with st.expander("Plot word cloud"):
                        plot_wordcloud(text)

                with st.expander('Download Results'):
                    file_download(token_analysis)