import streamlit as st import os.path import pathlib import pandas as pd import numpy as np import PyPDF2 from PyPDF2 import PdfReader from os import walk import nltk import glob import plotly.express as px from wordcloud import WordCloud import plotly.io as pio from plotly.subplots import make_subplots import plotly.graph_objs as go import pandas as pd import plotly.offline as pyo import io from io import StringIO #@st.cache_resource() @st.cache() def get_nl(): return nltk.download('punkt') get_nl() from nltk.tokenize import sent_tokenize from transformers import AutoTokenizer, AutoModelForSequenceClassification from transformers import pipeline # if os.path.exists("report.html"): # os.remove("report.html") #@st.cache_resource() @st.cache(allow_output_mutation=True) def get_sentiment_model(): tokenizer = AutoTokenizer.from_pretrained("ProsusAI/finbert") model = AutoModelForSequenceClassification.from_pretrained("ProsusAI/finbert") return tokenizer,model tokenizer_sentiment,model_sentiment = get_sentiment_model() @st.cache(allow_output_mutation=True) def get_emotion_model(): tokenizer = AutoTokenizer.from_pretrained("j-hartmann/emotion-english-distilroberta-base") model = AutoModelForSequenceClassification.from_pretrained("j-hartmann/emotion-english-distilroberta-base") return tokenizer,model tokenizer_emotion,model_emotion = get_emotion_model() @st.cache(allow_output_mutation=True) def get_intent_model(): classifier = pipeline("zero-shot-classification", model='cross-encoder/nli-deberta-v3-small') return classifier intent_classifier = get_intent_model() def extract_text_from_pdf(path): text='' reader = PdfReader(path) number_of_pages = len(reader.pages) print(number_of_pages) for i in range(number_of_pages): page=reader.pages[i] text = text + page.extract_text() return text # Create a button to download the HTML file def download_html(): with st.spinner('Downloading HTML file...'): # Get the HTML content with open('report.html', "r") as f: html = f.read() f.close() # Set the file name and content type file_name = "report.html" mime_type = "text/html" # Use st.download_button() to create a download button print('download button') st.download_button(label="Download Report", data=html, file_name=file_name, mime=mime_type) st.stop() if 'filename_key' not in st.session_state: st.session_state.filename_key = '' st.write(""" # Dcoument Analysis Tool """) #uploaded_file = st.file_uploader("Choose a PDF file") #uploaded_file = st.file_uploader("Choose a PDF file", accept_multiple_files=False, type=['pdf']) uploaded_file = st.file_uploader("Choose a PDF file", accept_multiple_files=True, type=['pdf']) #if uploaded_file is not None: if len(uploaded_file)==0: #print('none') st.session_state.filename_key = '' elif len(uploaded_file)>0: import time # Wait for 5 seconds time.sleep(5) pdf_reader = PyPDF2.PdfReader(uploaded_file[0]) num_pages = len(pdf_reader.pages) file_name = uploaded_file[0].name # st.write(st.session_state.filename_key) # print(file_name) # st.write("Filename:", file_name) if num_pages > 20: st.error("Pages in PDF file should be less than 20.") # Check that only one file was uploaded #elif isinstance(uploaded_file, list): elif len(uploaded_file) > 1: st.error("Please upload only one PDF file at a time.") elif st.session_state.filename_key == file_name: st.write("Report downloaded successfully") else: #uploaded_file = uploaded_file[0] # Check that the file is a PDF if uploaded_file[0].type != 'application/pdf': st.error("Please upload a PDF file.") else: ############################ 1. Extract text from PDF ############################ text='' # return text from pdf pdf_reader = PyPDF2.PdfReader(uploaded_file[0]) # Get the number of pages in the PDF file num_pages = len(pdf_reader.pages) # Display the number of pages in the PDF file st.write(f"Number of pages in PDF file: {num_pages}") for i in range(num_pages): page=pdf_reader.pages[i] text = text + page.extract_text() ############################ 2. Running models ############################ text = text.replace("\n", " " ) text = text.replace("$", "dollar " ) sentences = sent_tokenize(text) title = sentences[0] long_sentence=[] small_sentence=[] useful_sentence=[] for i in sentences: if len(i) > 510: long_sentence.append(i) elif len(i) < 50: small_sentence.append(i) else: useful_sentence.append(i) useful_sentence_len = len(useful_sentence) del sentences ############################ 2.1 Sentiment Modeling ############################ placeholder1 = st.empty() placeholder1.text('Performing Sentiment Analysis...') #with st.empty(): my_bar = st.progress(0) tokenizer = tokenizer_sentiment model = model_sentiment pipe = pipeline(model="ProsusAI/finbert") classifier = pipeline(model="ProsusAI/finbert") #output = classifier(useful_sentence) output=[] i=0 for temp in useful_sentence: output.extend(classifier(temp)) i=i+1 my_bar.progress(int((i/useful_sentence_len)*100)) my_bar.empty() df = pd.DataFrame.from_dict(output) df['Sentence']= pd.Series(useful_sentence) ############################ 2.2 Emotion Modeling ############################ #placeholder2 = st.empty() placeholder1.text('Performing Emotion Analysis...') # with st.empty(): my_bar = st.progress(0) tokenizer = tokenizer_emotion model = model_emotion classifier = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", top_k=1) output_emotion = [] i=0 for temp in useful_sentence: output_emotion.extend(classifier(temp)[0]) i=i+1 my_bar.progress(int((i/useful_sentence_len)*100)) my_bar.empty() placeholder1.text('Emotion Analysis Completed') ############################ 2.3 Intent Modeling ############################ placeholder1.text('Performing Intent Analysis...') my_bar = st.progress(0) candidate_labels = ['complaint', 'suggestion', 'query'] classifier = intent_classifier # temp_intent = classifier(useful_sentence, candidate_labels) # output_intent=[] # for temp in temp_intent: # output_intent.append({'label' : temp['labels'][0], 'score' : temp['scores'][0]}) output_intent=[] i=0 for temp1 in useful_sentence: temp = classifier(temp1, candidate_labels) output_intent.append({'label' : temp['labels'][0], 'score' : temp['scores'][0]}) i=i+1 my_bar.progress(int((i/useful_sentence_len)*100)) df_intent = pd.DataFrame.from_dict(output_intent) df_intent['Sentence']= pd.Series(useful_sentence) my_bar.empty() placeholder1.text('Processing Completed') ############################ 3. Processing ############################ ############################ 3.1. Sentiment Analysis ############################ # labels = ['neutral', 'positive', 'negative'] # values = df.label.value_counts().to_list() labels = ['neutral', 'positive', 'negative'] values = [df[df['label']=='neutral'].shape[0], df[df['label']=='positive'].shape[0], df[df['label']=='negative'].shape[0]] # removing words words_to_remove = ["s", "quarter", "thank", "million", "Thank", "quetion", 'wa', 'rate', 'firt', "customer", "business", "last year", "year", 'lat', 'well', 'jut', 'thi', 'cutomer', "will", "think", "higher", "question", "going"] for word in words_to_remove: text = text.replace(word, "") wordcloud = WordCloud(background_color='white', width=800, height=400).generate(text) image = wordcloud.to_image() pos_df = df[df['label']=='positive'] pos_df = pos_df[['score', 'Sentence']] pos_df = pos_df.sort_values('score', ascending=False) pos_df_mean = pos_df.score.mean() pos_df['score'] = pos_df['score'].round(4) pos_df.rename(columns = {'Sentence':'Positive Sentences'}, inplace = True) num_of_pos_sentences = pos_df.shape[0] if num_of_pos_sentences == 0: pos_df.loc[0] = [0.0, '-------No positive sentences found in report-------'] neg_df = df[df['label']=='negative'] neg_df = neg_df[['score', 'Sentence']] neg_df = neg_df.sort_values('score', ascending=False) neg_df_mean = neg_df.score.mean() neg_df['score'] = neg_df['score'].round(4) neg_df.rename(columns = {'Sentence':'Negative Sentences'}, inplace = True) num_of_neg_sentences = neg_df.shape[0] if num_of_neg_sentences == 0: neg_df.loc[0] = [0.0, '-------No negative sentences found in report-------'] neu_df = df[df['label']=='neutral'] neu_df = neu_df[['score', 'Sentence']] neu_df = neu_df.sort_values('score', ascending=False) #neu_df_mean = neu_df.score.mean() neu_df['score'] = neu_df['score'].round(4) neu_df.rename(columns = {'Sentence':'Neutral Sentences'}, inplace = True) num_of_neu_sentences = neu_df.shape[0] if num_of_neu_sentences == 0: neu_df.loc[0] = [0.0, '-------No neutral sentences found in report-------'] # df_temp = neg_df # df_temp = df_temp['score'] * -1 # df_temp = pd.concat([df_temp, pos_df]) df_temp = neg_df df_temp['score'] = df_temp['score'] * -1 df_temp_list = df_temp['score'].to_list() + pos_df['score'].to_list() mean = sum(df_temp_list) / len(df_temp_list) ############################ 3.2. Emotion Analysis ############################ df_emotion = pd.DataFrame.from_dict(output_emotion) df_emotion['Sentence']= pd.Series(useful_sentence) df_joy = df_emotion[df_emotion['label']=='joy'] df_joy = df_joy[['score', 'Sentence']] df_joy = df_joy.sort_values('score', ascending=False) df_joy['score'] = df_joy['score'].round(4) df_joy.rename(columns = {'Sentence':'Joy Sentences'}, inplace = True) num_of_joy_sentences = df_joy.shape[0] if num_of_joy_sentences == 0: df_joy.loc[0] = [0.0, '-------No joy sentences found in report-------'] df_sadness = df_emotion[df_emotion['label']=='sadness'] df_sadness = df_sadness[['score', 'Sentence']] df_sadness = df_sadness.sort_values('score', ascending=False) df_sadness['score'] = df_sadness['score'].round(4) df_sadness.rename(columns = {'Sentence':'Sad Sentences'}, inplace = True) num_of_sad_sentences = df_sadness.shape[0] if num_of_sad_sentences == 0: df_sadness.loc[0] = [0.0, '-------No sad sentences found in report-------'] df_anger = df_emotion[df_emotion['label']=='anger'] df_anger = df_anger[['score', 'Sentence']] df_anger = df_anger.sort_values('score', ascending=False) df_anger['score'] = df_anger['score'].round(4) df_anger.rename(columns = {'Sentence':'Angry Sentences'}, inplace = True) num_of_anger_sentences = df_anger.shape[0] if num_of_anger_sentences == 0: df_anger.loc[0] = [0.0, '-------No angry sentences found in report-------'] df_surprise = df_emotion[df_emotion['label']=='surprise'] df_surprise = df_surprise[['score', 'Sentence']] df_surprise = df_surprise.sort_values('score', ascending=False) df_surprise['score'] = df_surprise['score'].round(4) df_surprise.rename(columns = {'Sentence':'Surprised Sentences'}, inplace = True) num_of_surprise_sentences = df_surprise.shape[0] if num_of_surprise_sentences == 0: df_surprise.loc[0] = [0.0, '-------No surprised sentences found in report-------'] # df_temp_emotion = df_sadness # df_temp_emotion = pd.concat([df_sadness, df_anger]) # df_temp_emotion = df_temp_emotion['score'] * -1 # df_temp_emotion = pd.concat([df_temp_emotion, df_joy]) df_temp_emotion = df_sadness df_temp_emotion['score'] = df_temp_emotion['score'] * -1 df_temp_emotion_list = df_temp_emotion['score'].to_list() + df_joy['score'].to_list() emotion_mean = sum(df_temp_emotion_list) / len(df_temp_emotion_list) # df_temp = neg_df # df_temp['score'] = df_temp['score'] * -1 # df_temp_list = df_temp['score'].to_list() + pos_df['score'].to_list() # mean = sum(df_temp_list) / len(df_temp_list) ############################ 3.3. Intent Analysis ############################ df_query = df_intent[df_intent['label']=='query'] df_query = df_query[['score', 'Sentence']] df_query = df_query.sort_values('score', ascending=False) df_query['score'] = df_query['score'].round(4) df_query.rename(columns = {'Sentence':'Queries'}, inplace = True) df_query = df_query[df_query['score']>0.5] num_of_queries = df_query.shape[0] if num_of_queries == 0: df_query.loc[0] = [0.0, '-------No queries found in report-------'] df_complaint = df_intent[df_intent['label']=='complaint'] df_complaint = df_complaint[['score', 'Sentence']] df_complaint = df_complaint.sort_values('score', ascending=False) df_complaint['score'] = df_complaint['score'].round(4) df_complaint.rename(columns = {'Sentence':'Complaints'}, inplace = True) df_complaint = df_complaint[df_complaint['score']>0.5] num_of_complaints = df_complaint.shape[0] if num_of_complaints == 0: df_complaint.loc[0] = [0.0, '-------No complaints found in report-------'] df_suggestion = df_intent[df_intent['label']=='suggestion'] df_suggestion = df_suggestion[['score', 'Sentence']] df_suggestion = df_suggestion.sort_values('score', ascending=False) df_suggestion['score'] = df_suggestion['score'].round(4) df_suggestion.rename(columns = {'Sentence':'Suggestions'}, inplace = True) df_suggestion = df_suggestion[df_suggestion['score']>0.5] num_of_suggestions = df_suggestion.shape[0] if num_of_suggestions == 0: df_suggestion.loc[0] = [0.0, '-------No suggestions found in report-------'] total_num_of_intent = num_of_queries + num_of_complaints + num_of_suggestions ############################ 4. Plotting ############################ fig = make_subplots( rows=62, cols=6, specs=[ [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, {"type": "indicator", "rowspan": 3, "colspan": 2}, None, None, None], [None, None, None, None, None, None], [{"type": "pie", "rowspan": 6, "colspan": 2}, None, {"type": "indicator", "rowspan": 6, "colspan": 2}, None, {"type": "indicator", "rowspan": 6, "colspan": 2}, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [{"type": "image", "rowspan": 5, "colspan": 3}, None, None, {"type": "table", "rowspan": 5, "colspan": 3}, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [{"type": "table", "rowspan": 5, "colspan": 3}, None, None, {"type": "table", "rowspan": 5, "colspan": 3}, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, {"type": "indicator", "rowspan": 3, "colspan": 2}, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [{"type": "bar", "rowspan": 6, "colspan": 6}, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [{"type": "table", "rowspan": 2, "colspan": 3}, None, None, {"type": "table", "rowspan": 2, "colspan": 3}, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [{"type": "table", "rowspan": 2, "colspan": 3}, None, None, {"type": "table", "rowspan": 2, "colspan": 3}, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, {"type": "indicator", "rowspan": 3, "colspan": 2}, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, {"type": "indicator", "rowspan": 2, "colspan": 5}, None, None, None, None],#first bullet [None, None, None, None, None, None], [None, None, None, None, None, None], [None, {"type": "indicator", "rowspan": 2, "colspan": 5}, None, None, None, None], #2nd bullet [None, None, None, None, None, None], [None, None, None, None, None, None], [None, {"type": "indicator", "rowspan": 2, "colspan": 5}, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [{"type": "table", "rowspan": 4, "colspan": 2}, None, {"type": "table", "rowspan": 4, "colspan": 2}, None, {"type": "table", "rowspan": 4, "colspan": 2}, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], [None, None, None, None, None, None], ], ) ############################ 4.1. Sentiment Analysis ############################ fig.add_trace(go.Indicator( mode = "number", value = int(mean*100), number = {"suffix": "%"}, title = {"text": "Sentiment Analysis
Positivity Score"} ), row=4, col=3) colors = px.colors.diverging.Portland#RdBu fig.add_trace(go.Pie(labels=labels, values=values, hole = 0.5, title = 'Count by label', marker=dict(colors=colors, line=dict(width=2, color='white'))), row=6, col=1) fig.add_trace(go.Indicator( mode = "number", value = len(df.label.values.tolist()), title = {"text": "Count of Sentence"}), row=6, col=3) #fig.update_traces(title_text="Sentiment Analysis", selector=dict(type='indicator'), row=6, col=3) fig.add_trace(go.Indicator( mode = "gauge+number", value = mean, domain = {'x': [0, 1], 'y': [0, 1]}, title = {'text': "Average of Score", 'font': {'size': 16}}, gauge = { 'axis': {'range': [-1, 1], 'tickwidth': 1, 'tickcolor': "darkblue"}, 'bar': {'color': "darkblue"}, 'steps': [ {'range': [-0.29, 0.29], 'color': 'white'}, {'range': [0.3, 1], 'color': 'green'}, {'range': [-1, -0.3], 'color': 'red'} ], 'threshold': { 'line': {'color': "black", 'width': 4}, 'thickness': 0.75, 'value': abs((pos_df_mean - neg_df_mean)) } } ), row=6, col=5) if mean < -0.29: fig.update_traces(title_text="Cummulative Sentiment Negative", selector=dict(type='indicator'), row=6, col=5) elif mean < 0.29: fig.update_traces(title_text="Cummulative Sentiment Neutral", selector=dict(type='indicator'), row=6, col=5) else: fig.update_traces(title_text="Cummulative Sentiment Positive", selector=dict(type='indicator'), row=6, col=5) fig.add_trace(go.Image(z=image), row=13, col=1) fig.update_xaxes(visible=False, row=13, col=1) fig.update_yaxes(visible=False, row=13, col=1) table_trace1 = go.Table( header=dict(values=list(pos_df.columns), fill_color='lightgray', align='left'), cells=dict(values=[pos_df[name] for name in pos_df.columns], fill_color='white', align='left'), columnwidth=[1, 4] ) fig.add_trace(table_trace1, row=13, col=4) table_trace2 = go.Table( header=dict(values=list(neg_df.columns), fill_color='lightgray', align='left'), cells=dict(values=[neg_df[name] for name in neg_df.columns], fill_color='white', align='left'), columnwidth=[1, 4] ) fig.add_trace(table_trace2, row=18, col=4) table_trace2 = go.Table( header=dict(values=list(neu_df.columns), fill_color='lightgray', align='left'), cells=dict(values=[neu_df[name] for name in neu_df.columns], fill_color='white', align='left'), columnwidth=[1, 4] ) fig.add_trace(table_trace2, row=18, col=1) ########################### 4.2. Emotion Analysis ########################### fig.add_trace(go.Indicator( mode = "number", value = int(emotion_mean*100), number = {"suffix": "%"}, title = {"text": "Emotion Analysis
Happiness Score"} ), row=26, col=3) # Add bar chart colors_emotions = ['#174ecf', '#cfc517', '#940625', '#17cfcb'] emotion_bar_xlabels = ['Joy', 'Sadness', 'Anger', 'Surprise'] emotion_bar_ylabels = [num_of_joy_sentences, num_of_sad_sentences, num_of_anger_sentences, num_of_surprise_sentences] #annotations = [dict(x=x, y=y, text='😀', showarrow=False) for x, y in zip(emotion_bar_xlabels, emotion_bar_ylabels)] annotations = ['😀', '😞', '😡', '😯'] fig.add_trace( go.Bar(x=emotion_bar_xlabels, y= emotion_bar_ylabels, showlegend=True, marker_color=colors_emotions, text=annotations, textfont=dict(size=40)), row=29, col=1) fig.update_xaxes(title_text='Emotions', title_font=dict(size=16), row=29, col=1) fig.update_yaxes(title_text='Number of sentences', title_font=dict(size=16), row=29, col=1) # df_anger.loc[0] = [0.0, 'None'] # df_anger ################## happiness table table_trace2 = go.Table( header=dict(values=list(df_joy.columns), fill_color='lightgray', align='left'), cells=dict(values=[df_joy[name] for name in df_joy.columns], fill_color='white', align='left'), columnwidth=[1, 4] ) fig.add_trace(table_trace2, row=36, col=1) ################## sadness table table_trace2 = go.Table( header=dict(values=list(df_sadness.columns), fill_color='lightgray', align='left'), cells=dict(values=[df_sadness[name] for name in df_sadness.columns], fill_color='white', align='left'), columnwidth=[1, 4] ) fig.add_trace(table_trace2, row=36, col=4) ################## surprise table table_trace2 = go.Table( header=dict(values=list(df_surprise.columns), fill_color='lightgray', align='left'), cells=dict(values=[df_surprise[name] for name in df_surprise.columns], fill_color='white', align='left'), columnwidth=[1, 4] ) fig.add_trace(table_trace2, row=39, col=1) ################## anger table table_trace2 = go.Table( header=dict(values=list(df_anger.columns), fill_color='lightgray', align='left'), cells=dict(values=[df_anger[name] for name in df_anger.columns], fill_color='white', align='left'), columnwidth=[1, 4] ) fig.add_trace(table_trace2, row=39, col=4) ########################### 4.3. Intent Analysis ########################### fig.add_trace(go.Indicator( mode = "number", value = round(num_of_suggestions/max(num_of_complaints,0), 2), number = {"suffix": ""}, title = {"text": "Intent Analysis
Suggestion/Complaint Ratio"} ), row=44, col=3) fig.add_trace(go.Indicator( mode = "number+gauge", gauge = {'shape': "bullet", 'axis': {'range': [None, total_num_of_intent]}, 'bar': {'color': "blue"}}, #delta = {'reference': 300}, value = num_of_queries, #domain = {'x': [0.5, 1], 'y': [0.3, 0.9]}, title = {'text': "Queries"}), row=47, col=2) fig.add_trace(go.Indicator( mode = "number+gauge", gauge = {'shape': "bullet", 'axis': {'range': [None, total_num_of_intent]},}, #delta = {'reference': 300}, value = num_of_suggestions, #domain = {'x': [0.5, 1], 'y': [0.3, 0.9]}, title = {'text': "Suggestions"}), row=50, col=2) fig.add_trace(go.Indicator( mode = "number+gauge", gauge = {'shape': "bullet", 'axis': {'range': [None, total_num_of_intent]}, 'bar': {'color': "red"}}, #delta = {'reference': 300}, value = num_of_complaints, #domain = {'x': [0.5, 1], 'y': [0.3, 0.9]}, title = {'text': "Complaints"}), row=53, col=2) ############ query table table_trace2 = go.Table( header=dict(values=list(df_query.columns), fill_color='lightgray', align='left'), cells=dict(values=[df_query[name] for name in df_query.columns], fill_color='white', align='left'), columnwidth=[1, 4] ) fig.add_trace(table_trace2, row=56, col=1) ############ complaints table table_trace2 = go.Table( header=dict(values=list(df_complaint.columns), fill_color='lightgray', align='left'), cells=dict(values=[df_complaint[name] for name in df_complaint.columns], fill_color='white', align='left'), columnwidth=[1, 4] ) fig.add_trace(table_trace2, row=56, col=3) ############ suggestions table table_trace2 = go.Table( header=dict(values=list(df_suggestion.columns), fill_color='lightgray', align='left'), cells=dict(values=[df_suggestion[name] for name in df_suggestion.columns], fill_color='white', align='left'), columnwidth=[1, 4] ) fig.add_trace(table_trace2, row=56, col=5) import textwrap if len(title) > 120: title = title[:120] + '...' wrapped_title = "\n".join(textwrap.wrap(title, width=50)) # Add HTML tags to force line breaks in the title text wrapped_title = "
".join(wrapped_title.split("\n")) fig.update_layout(height=4000, showlegend=False, title={'text': f"{wrapped_title} - Text Analysis Report", 'x': 0.5, 'xanchor': 'center','font': {'size': 32}}) #pyo.plot(fig, filename='report.html') ############################## 5. Download Report ############################## buffer = io.StringIO() fig.write_html(buffer, include_plotlyjs='cdn') html_bytes = buffer.getvalue().encode() st.download_button( label='Download Report', data=html_bytes, file_name='report.html', mime='text/html' ) st.session_state.filename_key = file_name