Spaces:
Sleeping
Sleeping
File size: 3,772 Bytes
2120344 e684ac9 2120344 d0dd204 2120344 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 | import os
import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
# Configure page
st.set_page_config(page_title="CSV Illuminator", layout="wide")
st.title("📊 CSV Illuminator")
st.markdown("_Shedding light on hidden patterns in data with AI._")
# Set API Token (make sure environment variable is set in deployment)
HF_TOKEN = os.getenv("hf")
os.environ['HUGGINGFACEHUB_API_TOKEN'] = os.getenv("hf")
os.environ['hf'] = os.getenv("hf")
# Chat memory
if "chat_history" not in st.session_state:
st.session_state.chat_history = []
# Model setup
@st.cache_resource
def load_model():
endpoint = HuggingFaceEndpoint(
repo_id="deepseek-ai/DeepSeek-R1",
provider="nebius",
temperature=0.5,
max_new_tokens=200,
task="conversational"
)
return ChatHuggingFace(llm=endpoint)
model = load_model()
# File uploader
st.sidebar.header("📁 Upload Your CSV File")
uploaded_file = st.sidebar.file_uploader("Choose a CSV file", type=["csv"])
if uploaded_file:
try:
df = pd.read_csv(uploaded_file)
st.success("✅ File loaded successfully!")
# Dataset overview
with st.expander("📋 Dataset Overview", expanded=True):
st.write("**Shape:**", df.shape)
st.write("**Columns:**", df.columns.tolist())
st.write("**Missing Values:**")
st.dataframe(df.isnull().sum())
st.write("**Data Types:**")
st.dataframe(df.dtypes)
# AI-powered Q&A
st.subheader("💬 Ask a Question About Your Data")
user_question = st.text_input("Type your question here (e.g. 'What’s the average price?', 'Plot revenue by month')")
if user_question:
sample = df.head(50).to_csv(index=False)
prompt = f"""
You are a professional data analyst. The following is a sample of a dataset and a user question.
Answer clearly in plain English. If plotting is needed, return valid Python code using matplotlib or seaborn.
Dataset Preview:
{sample}
User Question: {user_question}
"""
with st.spinner("Analyzing your data..."):
try:
response = model.invoke([{"role": "user", "content": prompt}])
result = response.content if hasattr(response, "content") else response
st.session_state.chat_history.append((user_question, result))
st.markdown("### 🧠 Answer")
st.markdown(result)
except Exception as e:
st.error(f"Model error: {e}")
# Auto-plotting if user asks for a chart
if user_question and "plot" in user_question.lower():
st.subheader("📈 Auto-Generated Plot")
try:
numeric_cols = df.select_dtypes(include='number').columns.tolist()
if len(numeric_cols) >= 2:
fig, ax = plt.subplots()
sns.lineplot(data=df, x=numeric_cols[0], y=numeric_cols[1], ax=ax)
st.pyplot(fig)
else:
st.warning("Not enough numeric columns found for plotting.")
except Exception as e:
st.error(f"Plotting error: {e}")
# Chat history
if st.session_state.chat_history:
with st.expander("📚 Previous Interactions"):
for q, a in st.session_state.chat_history:
st.markdown(f"**🧍 You:** {q}")
st.markdown(f"**🤖 Bot:** {a}")
except Exception as e:
st.error(f"Error reading CSV: {e}")
else:
st.info("👈 Upload a CSV file to get started.")
|