import streamlit as st import pandas as pd import plotly.express as px # Set the page layout for Streamlit st.set_page_config(layout="wide") # Title and Introduction st.title("Data Visualization App") st.markdown(""" This app allows you to upload a table (CSV or Excel) and ask for graphs to visualize the data. Based on your question, the app will generate interactive graphs using **Plotly**. ### Available Features: - **Graph of a column**: Visualize a column as a graph. - **Scatter plot**: Visualize relationships between two columns. Upload your data and ask questions to generate visualizations. """) # File uploader in the sidebar file_name = st.sidebar.file_uploader("Upload file:", type=['csv', 'xlsx']) # File processing and question answering if file_name is None: st.markdown('

Please upload an excel or csv file

', unsafe_allow_html=True) else: try: # Check file type and handle reading accordingly if file_name.name.endswith('.csv'): df = pd.read_csv(file_name, sep=';', encoding='ISO-8859-1') # Adjust encoding if needed elif file_name.name.endswith('.xlsx'): df = pd.read_excel(file_name, engine='openpyxl') # Use openpyxl to read .xlsx files else: st.error("Unsupported file type") df = None if df is not None: numeric_columns = df.select_dtypes(include=['object']).columns for col in numeric_columns: df[col] = pd.to_numeric(df[col], errors='ignore') st.write("Original Data:") st.write(df) df_numeric = df.copy() df = df.astype(str) # Display the first 5 rows of the dataframe in an editable grid st.write("Sample data for graph generation:") st.write(df.head()) except Exception as e: st.error(f"Error reading file: {str(e)}") # User input for the graph query question = st.text_input('Ask your graph-related question') with st.spinner(): if st.button('Generate Graph'): try: if 'between' in question.lower() and 'and' in question.lower(): # Handle scatter plot (graph between two columns) columns = question.split('between')[-1].split('and') columns = [col.strip() for col in columns] if len(columns) == 2 and all(col in df.columns for col in columns): fig = px.scatter(df, x=columns[0], y=columns[1], title=f"Scatter Plot between {columns[0]} and {columns[1]}") st.plotly_chart(fig, use_container_width=True) st.success(f"Here is the scatter plot between '{columns[0]}' and '{columns[1]}'.") else: st.warning("Columns not found in the dataset.") elif 'column' in question.lower(): # Handle graph of a single column column = question.split('of')[-1].strip() if column in df.columns: fig = px.line(df, x=df.index, y=column, title=f"Graph of column '{column}'") st.plotly_chart(fig, use_container_width=True) st.success(f"Here is the graph of column '{column}'.") else: st.warning(f"Column '{column}' not found in the data.") else: st.warning("Please ask a valid graph-related question (e.g., 'make a graph between column1 and column2').") except Exception as e: st.warning(f"Error processing question or generating graph: {str(e)}")