app.py

import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures
from sklearn.pipeline import make_pipeline
from sklearn.svm import SVR
from sklearn.ensemble import RandomForestRegressor

st.title("Webcam Color Detection Charting")

uploaded_file = st.file_uploader("Choose a CSV file", type="csv")

time_frame_options = [
    "All",
    "1 second",
    "5 seconds",
    "10 seconds",
    "30 seconds",
    "1 minute",
    "5 minutes",
    "10 minutes",
    "30 minutes",
    "60 minutes",
]
time_frame = st.selectbox("Data Time Frame", time_frame_options)

regression_options = [
    "None",
    "Linear Regression",
    "Polynomial Regression",
    "SVR (Support Vector Regression)",
    "Random Forest Regression",
]
regression_type = st.selectbox("Regression Analysis Type", regression_options)

if uploaded_file is not None:
    # Read CSV file
    data = pd.read_csv(uploaded_file)

    # Filter data according to the time frame
    if time_frame != "All":
        seconds = {
            "1 second": 1,
            "5 seconds": 5,
            "10 seconds": 10,
            "30 seconds": 30,
            "1 minute": 60,
            "5 minutes": 300,
            "10 minutes": 600,
            "30 minutes": 1800,
            "60 minutes": 3600,
        }
        data['timestamp'] = pd.to_datetime(data['timestamp'], unit='ms')
        data.set_index('timestamp', inplace=True)
        data = data.resample(f"{seconds[time_frame]}S").mean().dropna().reset_index()

    # Create charts
    fig, axes = plt.subplots(2, 1, figsize=(10, 8))

    # RGB chart
    
color_space_options = ["RGB", "HSV"]
color_space = st.selectbox("Select Color Space", color_space_options)

# Depending on the selection, plot the corresponding values
if color_space == "RGB":
    axes[0].plot(data['R'], 'r', label='R')
    axes[0].plot(data['G'], 'g', label='G')
    axes[0].plot(data['B'], 'b', label='B')
elif color_space == "HSV":
    axes[0].plot(data['H'], 'r', label='H')
    axes[0].plot(data['S'], 'g', label='S')
    axes[0].plot(data['V'], 'b', label='V')
axes[0].legend(loc='upper right')


    axes[0].legend(loc='upper right')
    axes[0].set_title('RGB Values')
    axes[1].legend(loc='upper right')
    axes[1].set_title('HSV Values')

    # Perform regression analysis if selected
    if regression_type != "None":
        X = np.arange(len(data)).reshape(-1, 1)

        # Linear Regression
        if regression_type == "Linear Regression":
            model = LinearRegression()
            for color, code in zip(['R', 'G', 'B'], ['r', 'g', 'b']):
                model.fit(X, data[color])
                axes[0].plot(X, model.predict(X), f'{code}--')
                st.write(f"{color}: y = {model.coef_[0]} * x + {model.intercept_}")

        # Polynomial Regression
        elif regression_type == "Polynomial Regression":
            polynomial_features = PolynomialFeatures(degree=2)
            model = make_pipeline(polynomial_features, LinearRegression())
            for color, code in zip(['R', 'G', 'B'], ['r', 'g', 'b']):
                model.fit(X, data[color])
                axes[0].plot(X, model.predict(X), f'{code}--')
            st.write("Polynomial regression equation is not easily representable.")

        # SVR (Support Vector Regression)
        elif regression_type == "SVR (Support Vector Regression)":
            model = SVR()
            for color, code in zip(['R', 'G', 'B'], ['r', 'g', 'b']):
                model.fit(X, data[color])
                axes[0].plot(X, model.predict(X), f'{code}--')
            st.write("SVR equation is not easily representable.")

        # Random Forest Regression
        elif regression_type == "Random Forest Regression":
            model = RandomForestRegressor()
            for color, code in zip(['R', 'G', 'B'], ['r', 'g', 'b']):
                model.fit(X, data[color])
                axes[0].plot(X, model.predict(X), f'{code}--')
            st.write("Random Forest equation is not easily representable.")

    st.pyplot(fig)