Upload 11 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Designer.png filter=lfs diff=lfs merge=lfs -text

Procfile

@@ -0,0 +1 @@
+web: sh setup.sh && streamlit run app.py

app.py

@@ -0,0 +1,202 @@
+import streamlit as st
+import preprocessor, helper
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+# Define sections
+def home():
+    st.title("Welcome to WhatsApp Chat Analyzer")
+    st.markdown("""
+        ## Product Description
+        The WhatsApp Chat Analyzer is a powerful tool designed to help you gain insights from your WhatsApp chat data. By simply uploading your chat file, you can explore various metrics and visualizations that reveal patterns and trends in your conversations.
+
+        ## Features
+        - **Total Messages**: Count the total number of messages exchanged.
+        - **Word Analysis**: Analyze the total words used in the chat.
+        - **Media Analysis**: Count the number of media files shared.
+        - **Link Analysis**: Count the number of links shared.
+        - **Sentiment Analysis**: Understand the sentiment of the conversation.
+        - **Emoji Analysis**: Analyze the emojis used in the chat.
+        - **Monthly Timeline**: Visualize the number of messages sent each month.
+        - **Daily Timeline**: See daily message trends.
+        - **Activity Maps**: Discover the most active days and months.
+        - **Word Clouds**: Generate word clouds to see the most frequently used words.
+        - **Common Words**: Identify the most common words in the chat.
+        - **Busy Users**: Find out who is the most active user in the group.
+
+        ## How to Use It
+        1. **Upload File**: Choose your WhatsApp chat file (in `.txt` format) from the sidebar.
+        2. **Select User**: Select the user for whom you want to see the analysis or choose 'Overall' for group analysis.
+        3. **View Analysis**: Click on 'Show Analysis' to view detailed insights and visualizations.
+
+        ## Restrictions
+        - The app currently supports only `.txt` files exported from WhatsApp.
+        - Ensure the chat file is not too large to avoid performance issues.
+
+        ## Memory Size
+        - The app can handle files up to 200MB efficiently.
+        - Larger files may take more time to process and could impact performance.
+
+        ## Privacy and Security
+        - **Data Privacy**: Your uploaded chat data is processed locally and not stored on any server.
+        - **Security**: The app does not share your data with third parties. All processing is done in-memory and the data is discarded after the session ends.
+        
+        Enjoy analyzing your WhatsApp conversations with our interactive tools!
+    """)
+
+    # Add images
+    image_path1 = "Designer.png"
+    image_path = "downloadfile.jpg" # Update with the correct path to your image
+    st.image(image_path, caption="WhatsApp Chat Analysis", width=400)
+    st.image(image_path1, caption="WhatsApp Chat Analysis", width=400)
+
+def analyze():
+    st.title("WhatsApp Chat Analysis")
+    st.sidebar.title("WhatsApp Chat Analyzer")
+    uploaded_file = st.sidebar.file_uploader("Choose a file")
+
+    if uploaded_file is not None:
+        bytes_data = uploaded_file.getvalue()
+        data = bytes_data.decode("utf-8")
+        df = preprocessor.preprocess(data)
+
+        # fetch unique users
+        user_list = df['user'].unique().tolist()
+        user_list.remove('group_notification')
+        user_list.sort()
+        user_list.insert(0, "Overall")
+
+        selected_user = st.sidebar.selectbox("Show analysis wrt", user_list)
+
+        if st.sidebar.button("Show Analysis"):
+            # Stats Area
+            num_messages, words, num_media_messages, num_links = helper.fetch_stats(selected_user, df)
+            st.title("Top Statistics")
+            col1, col2, col3, col4 = st.columns(4)
+
+            with col1:
+                st.header("Total Messages")
+                st.title(num_messages)
+            with col2:
+                st.header("Total Words")
+                st.title(words)
+            with col3:
+                st.header("Media Shared")
+                st.title(num_media_messages)
+            with col4:
+                st.header("Links Shared")
+                st.title(num_links)
+
+            st.title("Sentiment Analysis")
+            sentiment_df = helper.sentiment_analysis(selected_user, df)
+            fig, ax = plt.subplots()
+            ax.bar(sentiment_df['sentiment_label'], sentiment_df['message'], color=['red', 'blue', 'green'])
+            st.pyplot(fig)
+
+            # Emoji analysis
+            st.title("Emoji Analysis")
+            emoji_df = helper.emoji_helper(selected_user, df)
+            col1, col2 = st.columns(2)
+
+            with col1:
+                st.dataframe(emoji_df)
+            with col2:
+                fig, ax = plt.subplots()
+                ax.pie(emoji_df[1].head(), labels=emoji_df[0].head(), autopct="%0.2f")
+                st.pyplot(fig)
+
+            # Monthly timeline
+            st.title("Monthly Timeline")
+            timeline = helper.monthly_timeline(selected_user, df)
+            fig, ax = plt.subplots()
+            ax.plot(timeline['time'], timeline['message'], color='green')
+            plt.xticks(rotation='vertical')
+            st.pyplot(fig)
+
+            # Daily timeline
+            st.title("Daily Timeline")
+            daily_timeline = helper.daily_timeline(selected_user, df)
+            fig, ax = plt.subplots()
+            ax.plot(daily_timeline['only_date'], daily_timeline['message'], color='black')
+            plt.xticks(rotation='vertical')
+            st.pyplot(fig)
+
+            # Activity map
+            st.title('Activity Map')
+            col1, col2 = st.columns(2)
+
+            with col1:
+                st.header("Most Busy Day")
+                busy_day = helper.week_activity_map(selected_user, df)
+                fig, ax = plt.subplots()
+                ax.bar(busy_day.index, busy_day.values, color='purple')
+                plt.xticks(rotation='vertical')
+                st.pyplot(fig)
+
+            with col2:
+                st.header("Most Busy Month")
+                busy_month = helper.month_activity_map(selected_user, df)
+                fig, ax = plt.subplots()
+                ax.bar(busy_month.index, busy_month.values, color='orange')
+                plt.xticks(rotation='vertical')
+                st.pyplot(fig)
+
+            st.title("Weekly Activity Map")
+            user_heatmap = helper.activity_heatmap(selected_user, df)
+            fig, ax = plt.subplots()
+            ax = sns.heatmap(user_heatmap)
+            st.pyplot(fig)
+
+            # Finding the busiest users in the group (Group level)
+            if selected_user == 'Overall':
+                st.title('Most Busy Users')
+                x, new_df = helper.most_busy_users(df)
+                fig, ax = plt.subplots()
+
+                col1, col2 = st.columns(2)
+
+                with col1:
+                    ax.bar(x.index, x.values, color='red')
+                    plt.xticks(rotation='vertical')
+                    st.pyplot(fig)
+                with col2:
+                    st.dataframe(new_df)
+
+            # WordCloud
+            st.title("Wordcloud")
+            df_wc = helper.create_wordcloud(selected_user, df)
+            fig, ax = plt.subplots()
+            ax.imshow(df_wc)
+            st.pyplot(fig)
+
+            # Most common words
+            most_common_df = helper.most_common_words(selected_user, df)
+            fig, ax = plt.subplots()
+            ax.barh(most_common_df[0], most_common_df[1])
+            plt.xticks(rotation='vertical')
+
+            st.title('Most Common Words')
+            st.pyplot(fig)
+
+            # Emoji analysis (repeated)
+            st.title("Emoji Analysis")
+            emoji_df = helper.emoji_helper(selected_user, df)
+            col1, col2 = st.columns(2)
+
+            with col1:
+                st.dataframe(emoji_df)
+            with col2:
+                fig, ax = plt.subplots()
+                ax.pie(emoji_df[1].head(), labels=emoji_df[0].head(), autopct="%0.2f")
+                st.pyplot(fig)
+
+# Sidebar navigation
+st.sidebar.title(" Whatsapp Chat Analyzer ")
+page = st.sidebar.radio("Go to", ["Home", "Analyze"])
+
+# Display the selected section
+if page == "Home":
+    home()
+elif page == "Analyze":
+    analyze()
+    

apps.py

@@ -0,0 +1,140 @@
+import streamlit as st
+import preprocessor,helper
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+st.sidebar.title("Whatsapp Chat Analyzer")
+
+uploaded_file = st.sidebar.file_uploader("Choose a file")
+
+if uploaded_file is not None:
+    bytes_data = uploaded_file.getvalue()
+    data = bytes_data.decode("utf-8")
+    df = preprocessor.preprocess(data)
+
+    # fetch unique users
+    user_list = df['user'].unique().tolist()
+    user_list.remove('group_notification')
+    user_list.sort()
+    user_list.insert(0,"Overall")
+
+    selected_user = st.sidebar.selectbox("Show analysis wrt",user_list)
+
+    if st.sidebar.button("Show Analysis"):
+
+        # Stats Area
+        num_messages, words, num_media_messages, num_links = helper.fetch_stats(selected_user,df)
+        st.title("Top Statistics")
+        col1, col2, col3, col4 = st.columns(4)
+
+        with col1:
+            st.header("Total Messages")
+            st.title(num_messages)
+        with col2:
+            st.header("Total Words")
+            st.title(words)
+        with col3:
+            st.header("Media Shared")
+            st.title(num_media_messages)
+        with col4:
+            st.header("Links Shared")
+            st.title(num_links)
+
+        # monthly timeline
+        st.title("Monthly Timeline")
+        timeline = helper.monthly_timeline(selected_user,df)
+        fig,ax = plt.subplots()
+        ax.plot(timeline['time'], timeline['message'],color='green')
+        plt.xticks(rotation='vertical')
+        st.pyplot(fig)
+
+        # daily timeline
+        st.title("Daily Timeline")
+        daily_timeline = helper.daily_timeline(selected_user, df)
+        fig, ax = plt.subplots()
+        ax.plot(daily_timeline['only_date'], daily_timeline['message'], color='black')
+        plt.xticks(rotation='vertical')
+        st.pyplot(fig)
+
+        # activity map
+        st.title('Activity Map')
+        col1,col2 = st.columns(2)
+
+        with col1:
+            st.header("Most busy day")
+            busy_day = helper.week_activity_map(selected_user,df)
+            fig,ax = plt.subplots()
+            ax.bar(busy_day.index,busy_day.values,color='purple')
+            plt.xticks(rotation='vertical')
+            st.pyplot(fig)
+
+        with col2:
+            st.header("Most busy month")
+            busy_month = helper.month_activity_map(selected_user, df)
+            fig, ax = plt.subplots()
+            ax.bar(busy_month.index, busy_month.values,color='orange')
+            plt.xticks(rotation='vertical')
+            st.pyplot(fig)
+
+        st.title("Weekly Activity Map")
+        user_heatmap = helper.activity_heatmap(selected_user,df)
+        fig,ax = plt.subplots()
+        ax = sns.heatmap(user_heatmap)
+        st.pyplot(fig)
+
+        # finding the busiest users in the group(Group level)
+        if selected_user == 'Overall':
+            st.title('Most Busy Users')
+            x,new_df = helper.most_busy_users(df)
+            fig, ax = plt.subplots()
+
+            col1, col2 = st.columns(2)
+
+            with col1:
+                ax.bar(x.index, x.values,color='red')
+                plt.xticks(rotation='vertical')
+                st.pyplot(fig)
+            with col2:
+                st.dataframe(new_df)
+
+        # WordCloud
+        st.title("Wordcloud")
+        df_wc = helper.create_wordcloud(selected_user,df)
+        fig,ax = plt.subplots()
+        ax.imshow(df_wc)
+        st.pyplot(fig)
+
+        # most common words
+        most_common_df = helper.most_common_words(selected_user,df)
+
+        fig,ax = plt.subplots()
+
+        ax.barh(most_common_df[0],most_common_df[1])
+        plt.xticks(rotation='vertical')
+
+        st.title('Most commmon words')
+        st.pyplot(fig)
+
+        # emoji analysis
+        emoji_df = helper.emoji_helper(selected_user,df)
+        st.title("Emoji Analysis")
+
+        col1,col2 = st.columns(2)
+
+        with col1:
+            st.dataframe(emoji_df)
+        with col2:
+            fig,ax = plt.subplots()
+            ax.pie(emoji_df[1].head(),labels=emoji_df[0].head(),autopct="%0.2f")
+            st.pyplot(fig)
+
+
+
+
+
+
+
+
+
+
+

helper.py

@@ -0,0 +1,126 @@
+from urlextract import URLExtract
+from wordcloud import WordCloud
+import pandas as pd
+from collections import Counter
+import emoji
+from nltk.sentiment.vader import SentimentIntensityAnalyzer
+import nltk
+
+nltk.download('vader_lexicon')
+
+extract = URLExtract()
+sentiment_analyzer = SentimentIntensityAnalyzer()
+
+def fetch_stats(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    # Number of messahes
+    num_messages = df.shape[0]
+
+    # fetch the total number of words
+    words = []
+    for message in df['message']:
+        words.extend(message.split())
+
+    # fetch number of media messages
+    num_media_messages = df[df['message'] == '<Media omitted>\n'].shape[0]
+
+    # fetch number of links shared
+    links = []
+    for message in df['message']:
+        links.extend(extract.find_urls(message))
+
+    return num_messages,len(words),num_media_messages,len(links)
+    #return num_messages, len(words), num_media_messages, len(links)
+
+def most_busy_users(df):
+    x = df['user'].value_counts().head()
+    df = round((df['user'].value_counts() / df.shape[0]) * 100, 2).reset_index().rename(
+        columns={'index': 'name', 'user': 'percent'})
+    return x, df
+
+def create_wordcloud(selected_user, df):
+    f = open('stop_hinglish.txt', 'r')
+    stop_words = f.read().splitlines()
+
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    temp = df[df['user'] != 'group_notification']
+    temp = temp[temp['message'] != '<Media omitted>\n']
+
+    def remove_stop_words(message):
+        y = [word for word in message.lower().split() if word not in stop_words]
+        return " ".join(y)
+
+    wc = WordCloud(width=500, height=500, min_font_size=10, background_color='white')
+    temp['message'] = temp['message'].apply(remove_stop_words)
+    df_wc = wc.generate(temp['message'].str.cat(sep=" "))
+    return df_wc
+
+def most_common_words(selected_user, df):
+    f = open('stop_hinglish.txt', 'r')
+    stop_words = f.read().splitlines()
+
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    temp = df[df['user'] != 'group_notification']
+    temp = temp[temp['message'] != '<Media omitted>\n']
+
+    words = [word for message in temp['message'] for word in message.lower().split() if word not in stop_words]
+    most_common_df = pd.DataFrame(Counter(words).most_common(20))
+    return most_common_df
+
+def emoji_helper(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    emojis = [c for message in df['message'] for c in message if c in emoji.UNICODE_EMOJI['en']]
+    emoji_df = pd.DataFrame(Counter(emojis).most_common(len(Counter(emojis))))
+    return emoji_df
+
+def monthly_timeline(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    timeline = df.groupby(['year', 'month_num', 'month']).count()['message'].reset_index()
+    timeline['time'] = timeline['month'] + "-" + timeline['year'].astype(str)
+    return timeline
+
+def daily_timeline(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    daily_timeline = df.groupby('only_date').count()['message'].reset_index()
+    return daily_timeline
+
+def week_activity_map(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    return df['day_name'].value_counts()
+
+def month_activity_map(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    return df['month'].value_counts()
+
+def activity_heatmap(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    user_heatmap = df.pivot_table(index='day_name', columns='period', values='message', aggfunc='count').fillna(0)
+    return user_heatmap
+
+def sentiment_analysis(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    df['sentiment'] = df['message'].apply(lambda x: sentiment_analyzer.polarity_scores(x))
+    df['sentiment_score'] = df['sentiment'].apply(lambda x: x['compound'])
+    df['sentiment_label'] = df['sentiment_score'].apply(lambda x: 'Positive' if x > 0 else ('Negative' if x < 0 else 'Neutral'))
+    sentiment_df = df.groupby('sentiment_label').count()['message'].reset_index()
+    return sentiment_df

preprocessor.py

@@ -0,0 +1,56 @@
+import re
+import pandas as pd
+import nltk
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
+
+nltk.download('stopwords')
+nltk.download('punkt')
+
+def preprocess(data):
+    pattern = '\d{1,2}/\d{1,2}/\d{2,4},\s\d{1,2}:\d{2}\s-\s'
+
+    messages = re.split(pattern, data)[1:]
+    dates = re.findall(pattern, data)
+
+    df = pd.DataFrame({'user_message': messages, 'message_date': dates})
+    df['message_date'] = pd.to_datetime(df['message_date'], format='%d/%m/%Y, %H:%M - ')
+
+    df.rename(columns={'message_date': 'date'}, inplace=True)
+
+    users = []
+    messages = []
+    for message in df['user_message']:
+        entry = re.split('([\w\W]+?):\s', message)
+        if entry[1:]:
+            users.append(entry[1])
+            messages.append(" ".join(entry[2:]))
+        else:
+            users.append('group_notification')
+            messages.append(entry[0])
+
+    df['user'] = users
+    df['message'] = messages
+    df.drop(columns=['user_message'], inplace=True)
+
+    df['only_date'] = df['date'].dt.date
+    df['year'] = df['date'].dt.year
+    df['month_num'] = df['date'].dt.month
+    df['month'] = df['date'].dt.month_name()
+    df['day'] = df['date'].dt.day
+    df['day_name'] = df['date'].dt.day_name()
+    df['hour'] = df['date'].dt.hour
+    df['minute'] = df['date'].dt.minute
+
+    period = []
+    for hour in df[['day_name', 'hour']]['hour']:
+        if hour == 23:
+            period.append(str(hour) + "-" + str('00'))
+        elif hour == 0:
+            period.append(str('00') + "-" + str(hour + 1))
+        else:
+            period.append(str(hour) + "-" + str(hour + 1))
+
+    df['period'] = period
+
+    return df

requirements.txt

@@ -0,0 +1,8 @@
+streamlit
+matplotlib
+seaborn
+urlextract
+wordcloud
+pandas
+emoji
+nltk

setup.sh

@@ -0,0 +1,9 @@
+mkdir -p ~/.streamlit/
+
+echo "\
+[server]\n\
+port = $PORT\n\
+enableCORS = false\n\
+headless = true\n\
+\n\
+" > ~/.streamlit/config.toml

stop_hinglish.txt

@@ -0,0 +1,1055 @@
+.
+..
+...
+?
+-
+--
+1
+2
+3
+4
+5
+6
+7
+8
+9
+0
+a
+aadi
+aaj
+aap
+aapne
+aata
+aati
+aaya
+aaye
+ab
+abbe
+abbey
+abe
+abhi
+able
+about
+above
+accha
+according
+accordingly
+acha
+achcha
+across
+actually
+after
+afterwards
+again
+against
+agar
+ain
+aint
+ain't
+aisa
+aise
+aisi
+alag
+all
+allow
+allows
+almost
+alone
+along
+already
+also
+although
+always
+am
+among
+amongst
+an
+and
+andar
+another
+any
+anybody
+anyhow
+anyone
+anything
+anyway
+anyways
+anywhere
+ap
+apan
+apart
+apna
+apnaa
+apne
+apni
+appear
+are
+aren
+arent
+aren't
+around
+arre
+as
+aside
+ask
+asking
+at
+aur
+avum
+aya
+aye
+baad
+baar
+bad
+bahut
+bana
+banae
+banai
+banao
+banaya
+banaye
+banayi
+banda
+bande
+bandi
+bane
+bani
+bas
+bata
+batao
+bc
+be
+became
+because
+become
+becomes
+becoming
+been
+before
+beforehand
+behind
+being
+below
+beside
+besides
+best
+better
+between
+beyond
+bhai
+bheetar
+bhi
+bhitar
+bht
+bilkul
+bohot
+bol
+bola
+bole
+boli
+bolo
+bolta
+bolte
+bolti
+both
+brief
+bro
+btw
+but
+by
+came
+can
+cannot
+cant
+can't
+cause
+causes
+certain
+certainly
+chahiye
+chaiye
+chal
+chalega
+chhaiye
+clearly
+c'mon
+com
+come
+comes
+could
+couldn
+couldnt
+couldn't
+d
+de
+dede
+dega
+degi
+dekh
+dekha
+dekhe
+dekhi
+dekho
+denge
+dhang
+di
+did
+didn
+didnt
+didn't
+dijiye
+diya
+diyaa
+diye
+diyo
+do
+does
+doesn
+doesnt
+doesn't
+doing
+done
+dono
+dont
+don't
+doosra
+doosre
+down
+downwards
+dude
+dunga
+dungi
+during
+dusra
+dusre
+dusri
+dvaara
+dvara
+dwaara
+dwara
+each
+edu
+eg
+eight
+either
+ek
+else
+elsewhere
+enough
+etc
+even
+ever
+every
+everybody
+everyone
+everything
+everywhere
+ex
+exactly
+example
+except
+far
+few
+fifth
+fir
+first
+five
+followed
+following
+follows
+for
+forth
+four
+from
+further
+furthermore
+gaya
+gaye
+gayi
+get
+gets
+getting
+ghar
+given
+gives
+go
+goes
+going
+gone
+good
+got
+gotten
+greetings
+guys
+haan
+had
+hadd
+hadn
+hadnt
+hadn't
+hai
+hain
+hamara
+hamare
+hamari
+hamne
+han
+happens
+har
+hardly
+has
+hasn
+hasnt
+hasn't
+have
+haven
+havent
+haven't
+having
+he
+hello
+help
+hence
+her
+here
+hereafter
+hereby
+herein
+here's
+hereupon
+hers
+herself
+he's
+hi
+him
+himself
+his
+hither
+hm
+hmm
+ho
+hoga
+hoge
+hogi
+hona
+honaa
+hone
+honge
+hongi
+honi
+hopefully
+hota
+hotaa
+hote
+hoti
+how
+howbeit
+however
+hoyenge
+hoyengi
+hu
+hua
+hue
+huh
+hui
+hum
+humein
+humne
+hun
+huye
+huyi
+i
+i'd
+idk
+ie
+if
+i'll
+i'm
+imo
+in
+inasmuch
+inc
+inhe
+inhi
+inho
+inka
+inkaa
+inke
+inki
+inn
+inner
+inse
+insofar
+into
+inward
+is
+ise
+isi
+iska
+iskaa
+iske
+iski
+isme
+isn
+isne
+isnt
+isn't
+iss
+isse
+issi
+isski
+it
+it'd
+it'll
+itna
+itne
+itni
+itno
+its
+it's
+itself
+ityaadi
+ityadi
+i've
+ja
+jaa
+jab
+jabh
+jaha
+jahaan
+jahan
+jaisa
+jaise
+jaisi
+jata
+jayega
+jidhar
+jin
+jinhe
+jinhi
+jinho
+jinhone
+jinka
+jinke
+jinki
+jinn
+jis
+jise
+jiska
+jiske
+jiski
+jisme
+jiss
+jisse
+jitna
+jitne
+jitni
+jo
+just
+jyaada
+jyada
+k
+ka
+kaafi
+kab
+kabhi
+kafi
+kaha
+kahaa
+kahaan
+kahan
+kahi
+kahin
+kahte
+kaisa
+kaise
+kaisi
+kal
+kam
+kar
+kara
+kare
+karega
+karegi
+karen
+karenge
+kari
+karke
+karna
+karne
+karni
+karo
+karta
+karte
+karti
+karu
+karun
+karunga
+karungi
+kaun
+kaunsa
+kayi
+kch
+ke
+keep
+keeps
+keh
+kehte
+kept
+khud
+ki
+kin
+kine
+kinhe
+kinho
+kinka
+kinke
+kinki
+kinko
+kinn
+kino
+kis
+kise
+kisi
+kiska
+kiske
+kiski
+kisko
+kisliye
+kisne
+kitna
+kitne
+kitni
+kitno
+kiya
+kiye
+know
+known
+knows
+ko
+koi
+kon
+konsa
+koyi
+krna
+krne
+kuch
+kuchch
+kuchh
+kul
+kull
+kya
+kyaa
+kyu
+kyuki
+kyun
+kyunki
+lagta
+lagte
+lagti
+last
+lately
+later
+le
+least
+lekar
+lekin
+less
+lest
+let
+let's
+li
+like
+liked
+likely
+little
+liya
+liye
+ll
+lo
+log
+logon
+lol
+look
+looking
+looks
+ltd
+lunga
+m
+maan
+maana
+maane
+maani
+maano
+magar
+mai
+main
+maine
+mainly
+mana
+mane
+mani
+mano
+many
+mat
+may
+maybe
+me
+mean
+meanwhile
+mein
+mera
+mere
+merely
+meri
+might
+mightn
+mightnt
+mightn't
+mil
+mjhe
+more
+moreover
+most
+mostly
+much
+mujhe
+must
+mustn
+mustnt
+mustn't
+my
+myself
+na
+naa
+naah
+nahi
+nahin
+nai
+name
+namely
+nd
+ne
+near
+nearly
+necessary
+neeche
+need
+needn
+neednt
+needn't
+needs
+neither
+never
+nevertheless
+new
+next
+nhi
+nine
+no
+nobody
+non
+none
+noone
+nope
+nor
+normally
+not
+nothing
+novel
+now
+nowhere
+o
+obviously
+of
+off
+often
+oh
+ok
+okay
+old
+on
+once
+one
+ones
+only
+onto
+or
+other
+others
+otherwise
+ought
+our
+ours
+ourselves
+out
+outside
+over
+overall
+own
+par
+pata
+pe
+pehla
+pehle
+pehli
+people
+per
+perhaps
+phla
+phle
+phli
+placed
+please
+plus
+poora
+poori
+provides
+pura
+puri
+q
+que
+quite
+raha
+rahaa
+rahe
+rahi
+rakh
+rakha
+rakhe
+rakhen
+rakhi
+rakho
+rather
+re
+really
+reasonably
+regarding
+regardless
+regards
+rehte
+rha
+rhaa
+rhe
+rhi
+ri
+right
+s
+sa
+saara
+saare
+saath
+sab
+sabhi
+sabse
+sahi
+said
+sakta
+saktaa
+sakte
+sakti
+same
+sang
+sara
+sath
+saw
+say
+saying
+says
+se
+second
+secondly
+see
+seeing
+seem
+seemed
+seeming
+seems
+seen
+self
+selves
+sensible
+sent
+serious
+seriously
+seven
+several
+shall
+shan
+shant
+shan't
+she
+she's
+should
+shouldn
+shouldnt
+shouldn't
+should've
+si
+sir
+sir.
+since
+six
+so
+soch
+some
+somebody
+somehow
+someone
+something
+sometime
+sometimes
+somewhat
+somewhere
+soon
+still
+sub
+such
+sup
+sure
+t
+tab
+tabh
+tak
+take
+taken
+tarah
+teen
+teeno
+teesra
+teesre
+teesri
+tell
+tends
+tera
+tere
+teri
+th
+tha
+than
+thank
+thanks
+thanx
+that
+that'll
+thats
+that's
+the
+theek
+their
+theirs
+them
+themselves
+then
+thence
+there
+thereafter
+thereby
+therefore
+therein
+theres
+there's
+thereupon
+these
+they
+they'd
+they'll
+they're
+they've
+thi
+thik
+thing
+think
+thinking
+third
+this
+tho
+thoda
+thodi
+thorough
+thoroughly
+those
+though
+thought
+three
+through
+throughout
+thru
+thus
+tjhe
+to
+together
+toh
+too
+took
+toward
+towards
+tried
+tries
+true
+truly
+try
+trying
+tu
+tujhe
+tum
+tumhara
+tumhare
+tumhari
+tune
+twice
+two
+um
+umm
+un
+under
+unhe
+unhi
+unho
+unhone
+unka
+unkaa
+unke
+unki
+unko
+unless
+unlikely
+unn
+unse
+until
+unto
+up
+upar
+upon
+us
+use
+used
+useful
+uses
+usi
+using
+uska
+uske
+usne
+uss
+usse
+ussi
+usually
+vaala
+vaale
+vaali
+vahaan
+vahan
+vahi
+vahin
+vaisa
+vaise
+vaisi
+vala
+vale
+vali
+various
+ve
+very
+via
+viz
+vo
+waala
+waale
+waali
+wagaira
+wagairah
+wagerah
+waha
+wahaan
+wahan
+wahi
+wahin
+waisa
+waise
+waisi
+wala
+wale
+wali
+want
+wants
+was
+wasn
+wasnt
+wasn't
+way
+we
+we'd
+well
+we'll
+went
+were
+we're
+weren
+werent
+weren't
+we've
+what
+whatever
+what's
+when
+whence
+whenever
+where
+whereafter
+whereas
+whereby
+wherein
+where's
+whereupon
+wherever
+whether
+which
+while
+who
+whoever
+whole
+whom
+who's
+whose
+why
+will
+willing
+with
+within
+without
+wo
+woh
+wohi
+won
+wont
+won't
+would
+wouldn
+wouldnt
+wouldn't
+y
+ya
+yadi
+yah
+yaha
+yahaan
+yahan
+yahi
+yahin
+ye
+yeah
+yeh
+yehi
+yes
+yet
+you
+you'd
+you'll
+your
+you're
+yours
+yourself
+yourselves
+you've
+yup