import gradio as gr
import pandas as pd

# Function to compare datasets
def compare_datasets(reference_file, user_file):
    # Read the Excel files
    reference_df = pd.read_excel(reference_file.name)
    user_df = pd.read_excel(user_file.name)

    # Flatten both datasets to 1D arrays of numbers (ignoring NaN and other non-numeric data)
    reference_numbers = reference_df.select_dtypes(include=['number']).values.flatten()
    user_numbers = user_df.select_dtypes(include=['number']).values.flatten()

    # Convert both arrays to sets for faster comparison
    reference_set = set(reference_numbers)
    user_set = set(user_numbers)

    # Find the numbers in the user's dataset that are present in the reference dataset
    common_numbers = reference_set.intersection(user_set)
    missing_numbers = reference_set.difference(user_set)

    # Prepare results
    if common_numbers:
        common_numbers_result = f"Found these numbers in the user's dataset: {', '.join(map(str, common_numbers))}"
    else:
        common_numbers_result = "No common numbers found."

    if missing_numbers:
        missing_numbers_result = f"Missing these numbers in the user's dataset: {', '.join(map(str, missing_numbers))}"
    else:
        missing_numbers_result = "All reference numbers are present."

    return common_numbers_result, missing_numbers_result

# Create the Gradio interface
iface = gr.Interface(
    fn=compare_datasets,
    inputs=[
        gr.File(label="Upload Your Reference Dataset (Excel)"),
        gr.File(label="Upload User's Dataset (Excel)"),
    ],
    outputs=[
        gr.Textbox(label="Common Numbers Found"),
        gr.Textbox(label="Missing Numbers"),
    ],
    title="Excel Dataset Comparison Tool",
    description="Upload your dataset and the user's dataset to check which numbers match and which are missing.",
)

# Launch the app
iface.launch()
import gradio as gr
import pandas as pd

# Function to compare datasets
def compare_datasets(reference_file, user_file):
    # Read the Excel files
    reference_df = pd.read_excel(reference_file.name)
    user_df = pd.read_excel(user_file.name)

    # Flatten both datasets to 1D arrays of numbers (ignoring NaN and other non-numeric data)
    reference_numbers = reference_df.select_dtypes(include=['number']).values.flatten()
    user_numbers = user_df.select_dtypes(include=['number']).values.flatten()

    # Convert both arrays to sets for faster comparison
    reference_set = set(reference_numbers)
    user_set = set(user_numbers)

    # Find the numbers in the user's dataset that are present in the reference dataset
    common_numbers = reference_set.intersection(user_set)
    missing_numbers = reference_set.difference(user_set)

    # Prepare results
    if common_numbers:
        common_numbers_result = f"Found these numbers in the user's dataset: {', '.join(map(str, common_numbers))}"
    else:
        common_numbers_result = "No common numbers found."

    if missing_numbers:
        missing_numbers_result = f"Missing these numbers in the user's dataset: {', '.join(map(str, missing_numbers))}"
    else:
        missing_numbers_result = "All reference numbers are present."

    return common_numbers_result, missing_numbers_result

# Create the Gradio interface
iface = gr.Interface(
    fn=compare_datasets,
    inputs=[
        gr.File(label="Upload Your Reference Dataset (Excel)"),
        gr.File(label="Upload User's Dataset (Excel)"),
    ],
    outputs=[
        gr.Textbox(label="Common Numbers Found"),
        gr.Textbox(label="Missing Numbers"),
    ],
    title="Excel Dataset Comparison Tool",
    description="Upload your dataset and the user's dataset to check which numbers match and which are missing.",
)

# Launch the app
iface.launch()