Update app.py

app.py

@@ -1,83 +1,134 @@
-import streamlit as st
+import os
+import csv
+import json
+import requests
+import re as r
+import gradio as gr
 import pandas as pd
-import numpy as np
-import plotly.express as px
-from wordcloud import WordCloud, STOPWORDS
-import matplotlib.pyplot as plt
+from transformers import pipeline
+from huggingface_hub import Repository
+from urllib.request import urlopen
 
-st.set_option('deprecation.showPyplotGlobalUse', False)
+HF_TOKEN = os.environ.get("HF_TOKEN")
+DATASET_NAME = "huggingface_sentiment_analysis_dataset"
+DATASET_REPO_URL = f"https://huggingface.co/datasets/pragnakalp/huggingface_sentiment_analysis_dataset"
+DATA_FILENAME = "hf_sentiment_logs.csv"
+DATA_FILE = os.path.join("hf_sentiment_logs", DATA_FILENAME)
+DATASET_REPO_ID = "pragnakalp/huggingface_sentiment_analysis_dataset"
+print("is none?", HF_TOKEN is None)
 
-DATA_ = pd.read_csv("Tweets.csv")
-st.title("Sentiment Analysis of Tweets about US Airlines")
-st.sidebar.title("Sentiment Analysis of Tweets about US Airlines")
-st.markdown("This application is a streamlit dashboard to analyze the sentiment of Tweets")
-st.sidebar.markdown("This application is a streamlit dashboard to analyze the sentiment of Tweets")
+input_para = "I am happy\nI am sad\nI am not feeling well\nHe is a very good person\nHe is bad person\nI love pineapple\nI hate mangoes"
 
-
-def run():
+try:
+    hf_hub_download(
+        repo_id=DATASET_REPO_ID,
+        filename=DATA_FILENAME,
+        cache_dir=DATA_DIRNAME,
+        force_filename=DATA_FILENAME
+    )
     
-    @st.cache(persist=True)
-    def load_data():
-        DATA_['tweet_created'] = pd.to_datetime(DATA_['tweet_created'])
-        return DATA_
-    data = load_data()
+except:
+    print("file not found")
+
+repo = Repository(
+    local_dir="hf_sentiment_logs", clone_from=DATASET_REPO_URL, use_auth_token=HF_TOKEN
+)
+
+def getIP():
+	d = str(urlopen('http://checkip.dyndns.com/')
+			.read())
+
+	return r.compile(r'Address: (\d+\.\d+\.\d+\.\d+)').search(d).group(1)
+
+def get_location(ip_addr):
+    ip=ip_addr
+
+    req_data={
+        "ip":ip,
+        "token":"pkml123"
+    }
+    url = "https://demos.pragnakalp.com/get-ip-location"
+
+    # req_data=json.dumps(req_data)
+    # print("req_data",req_data)
+    headers = {'Content-Type': 'application/json'}
+
+    response = requests.request("POST", url, headers=headers, data=json.dumps(req_data))
+    response = response.json()
+    print("response======>>",response)
+    return response
+
+def huggingface_result_page(paragraph):
+    if paragraph.strip():
+        model_base = pipeline('sentiment-analysis')
     
-    st.sidebar.subheader("Show random tweet")
-    random_tweet = st.sidebar.radio('Sentiment', ('positive', 'neutral', 'negative'))
-    st.sidebar.markdown(data.query('airline_sentiment == @random_tweet')[["text"]].sample(n=1).iat[0,0])
+        sen_list = paragraph
+        sen_list = sen_list.split('\n')
+        sen_list_temp = sen_list[0:]
+        results = []
+        temp_result_dict = []
     
-    st.sidebar.markdown("### Number of tweets by sentiment")
-    select = st.sidebar.selectbox('Visualization type', ['Histogram', 'Pie chart'])
-    sentiment_count = data['airline_sentiment'].value_counts()
-    sentiment_count = pd.DataFrame({'Sentiment':sentiment_count.index, 'Tweets':sentiment_count.values})
+        for sen in sen_list_temp:
+            sen = sen.strip()
     
-    if not st.sidebar.checkbox("Hide", True):
-        st.markdown("### Number of tweets by sentiment")
-        if select == "Histogram":
-            fig = px.bar(sentiment_count, x='Sentiment', y='Tweets', color='Tweets', height=500)
-            st.plotly_chart(fig)
-        else:
-            fig = px.pie(sentiment_count, values='Tweets', names='Sentiment')
-            st.plotly_chart(fig)
-            
+            if sen:
+                cur_result = model_base(sen)[0]
+                temp_result_dict.append(sen)
+                results.append(cur_result['label'])
     
-    st.sidebar.subheader("When and Where are users tweeting from?")
-    hour = st.sidebar.slider("Hour of day", 0,23)
-    modified_data = data[data['tweet_created'].dt.hour == hour]
-    if not st.sidebar.checkbox("Close", True, key='1'):
-        st.markdown("### Tweets locations based on the time of date")
-        st.markdown("%i tweets between %i:00 and %i:00" % (len(modified_data), hour, (hour+1)%24))
-        st.map(modified_data)
-        if st.sidebar.checkbox("Show Raw Data", False):
-            st.write(modified_data)
-    st.sidebar.subheader("Breakdown airline tweets by sentiment")
-    choice = st.sidebar.multiselect('Pick airline', ('US Airways', 'United', 'American', 'Southwest', 'Delta', 'Virgin America'), key='0')
-
-    if len(choice) > 0:
-        choice_data = data[data.airline.isin(choice)]
-        fig_choice = px.histogram(choice_data, x='airline',
-        y='airline_sentiment',
-        histfunc = 'count', color = 'airline_sentiment',
-        facet_col='airline_sentiment',
-        labels={'airline_sentiment':'tweets'}, height=600, width=800)
-        st.plotly_chart(fig_choice)
+        result = {
+            'Input': sen_list, 'Sentiment': results
+        }
+        print("LENGTH of results ====> ",str(len(results)))
+        print("LENGTH of sen_list ====> ",str(len(temp_result_dict)))
+        
+        return pd.DataFrame(result)
+    else:
+        raise gr.Error("Please enter text in inputbox!!!!")
+
+def save_data_and_sendmail(sen_list,results,result,paragraph):
+    try:
+        print("welcome")
+        ip_address = ''
+
+        ip_address= getIP()
+        print(ip_address)
+        location = get_location(ip_address)
+        print(location)
+        add_csv = [paragraph,result,ip_address,location]
+        with open(DATA_FILE, "a") as f:
+            writer = csv.writer(f)
+            # write the data
+            writer.writerow(add_csv)
+            commit_url = repo.push_to_hub()
+            print("commit data   :",commit_url)
+        
+        # url = 'https://pragnakalpdev35.pythonanywhere.com/HF_space_que_gen'
+        # # url = 'http://pragnakalpdev33.pythonanywhere.com/HF_space_question_generator'
+        # myobj = {'article': article,'total_que': num_que,'gen_que':result,'ip_addr':hostname.get("ip_addr",""),'host':hostname.get("host","")}
+        # x = requests.post(url, json = myobj) 
+        
+        url = 'https://pragnakalpdev33.pythonanywhere.com/HF_space_sentiment'
+        myobj = {'para': sen_list,'result':results,'ip_addr':ip_address,"location":location}
+        x = requests.post(url, json = myobj) 
+        
+        return "Successfully save data"
     
+    except Exception as e:
+        print("error")
+        return "Error while sending mail" + str(e)
+
+inputs = gr.Textbox(lines=3, label="Paragraph",value=input_para)
+outputs = gr.Dataframe(row_count = (3, "dynamic"), col_count=(2, "fixed"), label="Here is the Result", headers=["Input","Sentiment"],wrap=True)
+
+demo = gr.Interface(
+    huggingface_result_page,
+    inputs,
+    outputs,
+    title="Huggingface Sentiment Analysis",
+    css=".gradio-container {background-color: lightgray}",
+    article = """<p style='text-align: center;'>Feel free to give us your <a href="https://www.pragnakalp.com/contact/" target="_blank">feedback</a> on this Question Generation using T5 demo.</p>
+                                        <p style='text-align: center;'>Developed by: <a href="https://www.pragnakalp.com" target="_blank">Pragnakalp Techlabs</a></p>"""
+)
 
-    st.sidebar.header("Word Cloud")
-    word_sentiment = st.sidebar.radio('Display word cloud for what sentiment?',('positive', 'neutral','negative'))
-
-    if not st.sidebar.checkbox("Close", True, key='3'):
-        st.header('Word cloud for %s sentiment' % (word_sentiment))
-        df = data[data['airline_sentiment']==word_sentiment]
-        words = ' '.join(df['text'])
-        processed_words = ' '.join([word for word in words.split() if 'http' not in word and not word.startswith('@') and word !='RT'])
-        wordcloud = WordCloud(stopwords=STOPWORDS,
-        background_color='white', height=640, width=800).generate(processed_words)
-        plt.imshow(wordcloud)
-        plt.xticks([])
-        plt.yticks([])
-        st.pyplot() 
-            
-            
-if __name__ == '__main__':
-    run()
+demo.launch()