Chat with Netflix Data and Auto-Generate Charts Using AI (No Coding Needed)

Build a Smart Netflix Dashboard That Answers You with Charts

What if you could ask a dataset a question—and get back a chart? In this beginner-friendly tutorial, you’ll create a Streamlit app that does exactly that:

• Loads Netflix data into your browser
• Lets you ask questions using plain English
• Uses AI to answer your question and dynamically generate a chart

No coding experience? No problem. Follow these steps and you'll have it running locally in minutes.

🧰 What You’ll Need

1. Python installed from python.org
2. Netflix dataset from Kaggle - Netflix Shows
3. A free OpenAI API key from platform.openai.com
   You may need to pre-purchase credits to use the API in this sample app.

📁 Setup Instructions

1. Create a folder called netflix-ai-dashboard
2. Place netflix_titles.csv inside that folder
3. Install the required Python libraries:

   pip install streamlit pandas matplotlib openai

📄 Full App Code (app.py)

Create a new file called app.py inside your folder and paste this entire code:

import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt
from openai import OpenAI
import io
import re
import textwrap

st.set_page_config(page_title="Netflix AI Chart Assistant", layout="centered")
st.title("📺 Ask AI to Analyze Netflix Data & Generate Charts")

# Load Netflix dataset
@st.cache_data
def load_data():
    df = pd.read_csv("netflix_titles.csv")
    df.dropna(subset=["type", "release_year", "country"], inplace=True)
    return df

df = load_data()

# Dataset preview
with st.expander("🔍 Preview Netflix Data"):
    st.dataframe(df.head(20))

# User inputs
st.subheader("🤖 Ask AI About the Netflix Data")

api_key = st.text_input("Enter your OpenAI API Key", type="password")
st.caption("Don't have a key? Get one at [platform.openai.com](https://platform.openai.com/account/api-keys)")
st.markdown(":warning: **Note:** If you see a quota or billing error, you may need to [add credits to your OpenAI account](https://platform.openai.com/account/billing).")

question = st.text_area("Ask a question about the dataset", placeholder="e.g. What countries produce the most Netflix content?")

# Ask AI and Generate Chart
if st.button("Ask AI and Generate Chart"):
    if not api_key or not question:
        st.warning("Please enter both your API key and a question.")
    else:
        with st.spinner("Asking AI..."):
            try:
                client = OpenAI(api_key=api_key)

                # Limit data sent to AI for performance
                data_csv = df.head(100).to_csv(index=False)

                # Compose the prompt
                prompt = f"""
You are a helpful data analyst. Based on the Netflix data sample below:

{data_csv}

Answer this question: "{question}"

Your response should include:
1. A short written answer
2. A markdown summary table (max 10 rows)
3. A Python matplotlib code block to generate a relevant chart using the sample data (assume it's in a DataFrame called df)

Only include one chart. Return the Python code as a single code block.
"""

                response = client.chat.completions.create(
                    model="gpt-3.5-turbo",
                    messages=[{"role": "user", "content": prompt}],
                    temperature=0.5
                )

                reply = response.choices[0].message.content
                st.markdown("### 🧠 AI Analysis:")
                st.markdown(reply)

                # Extract and execute chart code
                code_blocks = re.findall(r"```(?:python)?\n(.*?)```", reply, re.DOTALL)
                if code_blocks:
                    st.markdown("### 📊 AI-Generated Chart:")
                    try:
                        exec_globals = {"df": df.head(100), "plt": plt}
                        exec(textwrap.dedent(code_blocks[0]), exec_globals)
                        st.pyplot(plt)
                        plt.clf()
                    except Exception as chart_error:
                        st.error(f"Chart code could not be run: {chart_error}")
                else:
                    st.warning("No Python chart code found in AI's response.")
            except Exception as e:
                st.error(f"Something went wrong: {e}")

▶️ Run the App

In your terminal, navigate to the project folder and run:

streamlit run app.py

Then visit http://localhost:8501 in your browser.

🧠 Sample Questions to Try

• What are the top 5 genres in this sample?
• Which countries produce the most Netflix content?
• How many movies vs TV shows are there?
• Can you plot releases by year?

🛠️ Best Practices

• Send only 50–100 rows to the AI for speed and cost efficiency
• Always wrap AI-generated Python in a try block
• Don’t hardcode or share your API key—treat it like a password

🎉 What You Built

You now have an AI-powered data assistant that:

• Loads and filters real Netflix data
• Answers questions in plain English
• Generates custom summary tables and charts from your data

This is a great foundation for dashboards, research assistants, or even business tools!

What’s the best chart AI made for you? Share it below!