dataframe.py

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import streamlit as st

# Function to process CSV files
def process_csv(files):
    dfs = []
    for file in files:
        df = pd.read_csv(file)
        dfs.append(df)
    combined_df = pd.concat(dfs, ignore_index=True)
    return combined_df, dfs

# Function to process Excel files
def process_excel(files):
    dfs = []
    for file in files:
        df = pd.read_excel(file)
        dfs.append(df)
    combined_df = pd.concat(dfs, ignore_index=True)
    return combined_df, dfs

# Function to process TXT files
def process_texts(files):
    texts = []
    for file in files:
        file_content = file.read().decode('utf-8')
        text = Document(page_content=file_content)
        texts.append(text)
    combined_text = "\n\n".join(text.page_content for text in texts)
    return combined_text, texts

# Function to process PDF files
def process_pdfs(files):
    texts = []
    for file in files:
        reader = PdfReader(file)
        text = ""
        for page in reader.pages:
            text += page.extract_text()
        texts.append(Document(page_content=text))
    combined_text = "\n\n".join(text.page_content for text in texts)
    return combined_text, texts

# Function to generate insights from a dataframe
def generate_insights(query, df):
    response = ""
    if query.lower() == "show dataframe":
        st.dataframe(df)
        response = "Displayed the dataframe."
    elif query.lower() == "show summary":
        st.write(df.describe())
        response = "Displayed the statistical summary of the dataframe."
    else:
        try:
            if "plot" in query.lower():
                col = query.split(" ")[-1]
                if col in df.columns:
                    plt.figure(figsize=(10, 5))
                    sns.histplot(df[col], kde=True)
                    st.pyplot(plt)
                    response = f"Displayed the distribution plot for {col}."
                else:
                    response = f"Column {col} not found in the dataframe."
            else:
                response = f"Query '{query}' not recognized."
        except Exception as e:
            response = f"An error occurred: {e}"
    return response