| import streamlit as st | |
| import time | |
| import pandas as pd | |
| import io | |
| from transformers import pipeline | |
| from streamlit_extras.stylable_container import stylable_container | |
| import json | |
| import plotly.express as px | |
| st.subheader("AI CSV and XLSX Data Analyzer", divider="blue") | |
| st.link_button("by nlpblogs", "https://nlpblogs.com", type="tertiary") | |
| expander = st.expander("**Important notes on the AI CSV and XLSX Data Analyzer**") | |
| expander.write( | |
| """ | |
| **Supported File Formats:** This app accepts files in .csv and .xlsx formats. | |
| **How to Use:** Upload your file first. Select two different columns from your data to visualize in a Tree Map. Then, type your question into the text area provided and click the 'Retrieve your answer' button. | |
| **Tree Map:** Your uploaded data is presented in an interactive Tree Map for visual exploration. Click on any area within the map to access specific data insights. | |
| **Usage Limits:** You can ask up to 10 questions. | |
| **Subscription Management:** This app offers a one-day free trial, followed by a one-day subscription, expiring after 24 hours. If you are interested in building your own AI CSV and XLSX Data Analyzer, we invite you to explore our NLP Web App Store on our website. You can select your desired features, place your order, and we will deliver your custom app in five business days. If you wish to delete your Account with us, please contact us at [email protected] | |
| **Customization:** To change the app's background color to white or black, click the three-dot menu on the right-hand side of your app, go to Settings and then Choose app theme, colors and fonts. | |
| **File Handling and Errors:** (a) The app may provide an inaccurate answer if the information is missing from the relevant cell. (b) The app may display an error message if your file has errors, date values or float numbers (0.5, 1.2, 4.5 etc.). | |
| For any errors or inquiries, please contact us at [email protected] | |
| """ | |
| ) | |
| with st.sidebar: | |
| container = st.container(border=True) | |
| container.write( | |
| "**Question-Answering (QA)** is the task of retrieving the answer to a question from a given text (knowledge base), which is used as context." | |
| ) | |
| st.subheader("Related NLP Web Apps", divider="blue") | |
| st.link_button( | |
| "AI Google Sheet Data Analyzer", | |
| "https://nlpblogs.com/shop/table-question-answering-qa/google-sheet-qa-demo-app/", | |
| type="primary", | |
| ) | |
| if "question_attempts" not in st.session_state: | |
| st.session_state["question_attempts"] = 0 | |
| max_attempts = 10 | |
| MAX_FILE_SIZE_KB = 10 | |
| MAX_FILE_SIZE_BYTES = MAX_FILE_SIZE_KB * 1024 | |
| upload_file = st.file_uploader( | |
| f"Upload your file **max 10 KB**. Accepted file formats include: .csv, .xlsx", | |
| type=['csv', 'xlsx'] | |
| ) | |
| if upload_file is not None: | |
| if upload_file.size > MAX_FILE_SIZE_BYTES: | |
| st.error(f"Error: The uploaded file is too large. Maximum allowed size is {MAX_FILE_SIZE_KB} KB.") | |
| else: | |
| st.success("File uploaded successfully!") | |
| file_extension = upload_file.name.split('.')[-1].lower() | |
| try: | |
| if file_extension == 'csv': | |
| df_original = pd.read_csv(upload_file, na_filter=False) | |
| elif file_extension == 'xlsx': | |
| df_original = pd.read_excel(upload_file, na_filter=False) | |
| else: | |
| st.warning("Unsupported file type.") | |
| st.stop() | |
| if df_original.isnull().values.any(): | |
| st.error("Error: The file contains missing values.") | |
| st.stop() | |
| else: | |
| st.session_state.df_original = df_original | |
| all_columns = df_original.columns.tolist() | |
| st.divider() | |
| st.write("Select two different columns from your data to visualize in a **Tree Map**. ") | |
| parent_column = st.selectbox("Select the parent column:", all_columns) | |
| value_column = st.selectbox("Select the value column:", all_columns) | |
| if parent_column and value_column: | |
| if parent_column == value_column: | |
| st.warning("Warning: You have selected the same column for both the parent and value column. Please select two different columns from your data.") | |
| else: | |
| df_treemap = df_original.copy() | |
| path_columns = [px.Constant("all"), parent_column, value_column] | |
| fig = px.treemap(df_treemap, path=path_columns) | |
| fig.update_layout(margin=dict(t=50, l=25, r=25, b=25)) | |
| st.subheader("Tree Map", divider="blue") | |
| st.plotly_chart(fig) | |
| st.subheader("Uploaded File", divider="blue") | |
| st.dataframe(df_original, key="uploaded_dataframe") | |
| st.write(f"_Number of rows_: {df_original.shape[0]}") | |
| st.write(f"_Number of columns_: {df_original.shape[1]}") | |
| except pd.errors.ParserError: | |
| st.error("Error: The CSV file is not readable or is incorrectly formatted.") | |
| st.stop() | |
| except UnicodeDecodeError: | |
| st.error("Error: The CSV file could not be decoded.") | |
| st.stop() | |
| except ValueError: | |
| st.error("Error: The Excel file is not readable or is incorrectly formatted.") | |
| st.stop() | |
| except Exception as e: | |
| st.error(f"An unexpected error occurred: {e}") | |
| st.stop() | |
| st.divider() | |
| def clear_question(): | |
| st.session_state["question"] = "" | |
| question = st.text_input( | |
| "Type one question at a time and then press **Retrieve your answer**:", key="question" | |
| ) | |
| st.button("Clear question", on_click=clear_question) | |
| if st.button("Retrieve your answer"): | |
| if st.session_state["question_attempts"] >= max_attempts: | |
| st.error(f"You have asked {max_attempts} questions. Maximum question attempts reached.") | |
| st.stop() | |
| st.session_state["question_attempts"] += 1 | |
| with st.spinner("Wait for it...", show_time=True): | |
| time.sleep(5) | |
| if "df_original" in st.session_state and st.session_state.df_original is not None: | |
| tqa = pipeline( | |
| task="table-question-answering", | |
| model="microsoft/tapex-large-finetuned-wtq", | |
| ) | |
| try: | |
| answer = tqa(table=st.session_state.df_original, query=question)["answer"] | |
| st.write(answer) | |
| except Exception as e: | |
| st.error(f"An error occurred during question answering: {e}") | |
| st.error(f"Error details: {e}") | |
| else: | |
| st.warning("Please upload a file first to ask questions.") | |
| st.divider() | |
| st.write( | |
| f"Number of questions asked: {st.session_state['question_attempts']}/{max_attempts}" | |
| ) | |