File size: 3,510 Bytes
08ae01a 456a22b 08ae01a 0e577d5 cc768a9 08ae01a 456a22b 08ae01a |
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 |
import streamlit as st
import pandas as pd
import pickle
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from transformers import pipeline
from PyPDF2 import PdfReader
# Helper function to load different file types
def load_file(uploaded_file):
if uploaded_file.name.endswith('.csv'):
return pd.read_csv(uploaded_file)
elif uploaded_file.name.endswith('.xlsx'):
return pd.read_excel(uploaded_file)
elif uploaded_file.name.endswith('.pdf'):
reader = PdfReader(uploaded_file)
text = ''.join(page.extract_text() for page in reader.pages)
# PDF parsing logic here (customized for table extraction)
raise NotImplementedError("PDF parsing is not implemented.")
else:
raise ValueError("Unsupported file format. Please upload CSV, Excel, or PDF.")
# Train the model if it doesn't already exist
def train_model(data):
data['Hour'] = pd.to_datetime(data['Timestamp']).dt.hour
#data['Hour'] = pd.to_datetime(data['Timestamp']).dt.hour
X = data[['Hour', 'Temperature', 'CloudCover']]
#,'DATE_TIME','PLANT_ID','SOURCE_KEY','DC_POWER','AC_POWER','DAILY_YIELD','TOTAL_YIELD'
y = data['SolarOutput']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
model = LinearRegression()
model.fit(X_train, y_train)
with open('solar_model.pkl', 'wb') as f:
pickle.dump(model, f)
return model
# Load the trained model
def load_model():
try:
with open('solar_model.pkl', 'rb') as f:
return pickle.load(f)
except FileNotFoundError:
return None
# Initialize the text generation pipeline
generator = pipeline('text-generation', model='gpt2', device=-1)
# Streamlit app
st.title("Smart Home Energy Advisor")
# File uploader
uploaded_file = st.file_uploader("Upload your data file (CSV, Excel, or PDF)", type=['csv', 'xlsx', 'pdf'])
#uploaded_file = "/solar_data.csv"
if uploaded_file:
# Load and preprocess data
try:
data = load_file(uploaded_file)
st.write("Data Preview:", data.head())
except Exception as e:
st.error(f"Error loading file: {e}")
data = None
if data is not None:
# Load or train the model
model = load_model()
if not model:
st.warning("No pre-trained model found. Training a new model...")
model = train_model(data)
st.success("Model trained and saved successfully!")
# Preprocess data
data['Hour'] = pd.to_datetime(data['Timestamp']).dt.hour
data['PredictedSolarOutput'] = model.predict(data[['Hour', 'Temperature', 'CloudCover']])
# Determine the best hour for maximum solar energy
best_hour = data.loc[data['PredictedSolarOutput'].idxmax(), 'Hour']
# Generate advice
advice_prompt = f"The best time to use your appliances is between {best_hour}:00 and {best_hour + 2}:00."
advice = generator(advice_prompt, max_length=50)[0]['generated_text']
# Display predictions and advice
st.subheader("Predictions")
st.write(data)
st.subheader("Recommendation")
st.write(advice)
# Chatbot feature
st.subheader("Chat with the Advisor")
user_query = st.text_input("Ask your question:")
if user_query:
chatbot_response = generator(f"User asked: {user_query}. Response:", max_length=50)[0]['generated_text']
st.write("Advisor Response:", chatbot_response) |