Spaces:
Sleeping
Sleeping
import streamlit as st | |
import yfinance as yf | |
import pandas as pd | |
from prophet import Prophet | |
import plotly.graph_objs as go | |
import google.generativeai as genai | |
import numpy as np | |
# Streamlit app details | |
st.set_page_config(page_title="TechyTrade", layout="wide") | |
# Custom CSS | |
st.markdown(""" | |
<style> | |
@import url('https://fonts.googleapis.com/css2?family=Montserrat:wght@300;400;700&display=swap'); | |
body { | |
background-color: #f4f4f9; | |
color: #333; | |
font-family: 'Montserrat', sans-serif; | |
} | |
.sidebar .sidebar-content { | |
background-color: #2c3e50; | |
color: white; | |
} | |
h1, h2, h3 { | |
color: #2980b9; | |
} | |
.css-1v3fvcr { | |
color: #2980b9 !important; | |
} | |
.css-17eq0hr { | |
font-family: 'Montserrat', sans-serif !important; | |
} | |
.css-2trqyj { | |
font-family: 'Montserrat', sans-serif !important; | |
} | |
</style> | |
""", unsafe_allow_html=True) | |
# Sidebar | |
with st.sidebar: | |
st.title("๐ TechyTrade") | |
ticker = st.text_input("Enter a stock ticker (e.g. AAPL) ๐ท๏ธ", "AAPL") | |
period = st.selectbox("Enter a time frame โณ", ("1D", "5D", "1M", "6M", "YTD", "1Y", "5Y"), index=2) | |
forecast_period = st.slider("Select forecast period (days) ๐ฎ", min_value=1, max_value=365, value=30) | |
st.write("Select Technical Indicators:") | |
sma_checkbox = st.checkbox("Simple Moving Average (SMA)") | |
ema_checkbox = st.checkbox("Exponential Moving Average (EMA)") | |
rsi_checkbox = st.checkbox("Relative Strength Index (RSI)") | |
macd_checkbox = st.checkbox("Moving Average Convergence Divergence (MACD)") | |
bollinger_checkbox = st.checkbox("Bollinger Bands") | |
google_api_key = st.text_input("Enter your Google API Key ๐", type="password") | |
button = st.button("Submit ๐") | |
# Load generative model | |
def load_model(api_key): | |
genai.configure(api_key=api_key) | |
return genai.GenerativeModel('gemini-1.5-flash') | |
# Function to generate reasons using the generative model | |
def generate_reasons(fig, stock_info, price_info, biz_metrics, api_key): | |
model = load_model(api_key) | |
prompt = f"Based on the following stock price graph description:\n\n{fig}\n\n and the tables:\n\n{stock_info}\n\n and\n\n{price_info}\n\n and\n\n{biz_metrics}\n\n and analyze the trends and give recommendations and insights." | |
response = model.generate_content(prompt) | |
return response.text | |
# Function to format large numbers | |
def format_value(value): | |
suffixes = ["", "K", "M", "B", "T"] | |
suffix_index = 0 | |
while value >= 1000 and suffix_index < len(suffixes) - 1: | |
value /= 1000 | |
suffix_index += 1 | |
return f"${value:.1f}{suffixes[suffix_index]}" | |
# Technical Indicators Functions | |
def calculate_sma(data, window): | |
return data.rolling(window=window).mean() | |
def calculate_ema(data, window): | |
return data.ewm(span=window, adjust=False).mean() | |
def calculate_rsi(data, window): | |
delta = data.diff() | |
gain = (delta.where(delta > 0, 0)).rolling(window=window).mean() | |
loss = (-delta.where(delta < 0, 0)).rolling(window=window).mean() | |
rs = gain / loss | |
return 100 - (100 / (1 + rs)) | |
def calculate_macd(data, short_window=12, long_window=26, signal_window=9): | |
short_ema = calculate_ema(data, short_window) | |
long_ema = calculate_ema(data, long_window) | |
macd = short_ema - long_ema | |
signal = calculate_ema(macd, signal_window) | |
return macd, signal | |
def calculate_bollinger_bands(data, window): | |
sma = calculate_sma(data, window) | |
std = data.rolling(window=window).std() | |
upper_band = sma + (std * 2) | |
lower_band = sma - (std * 2) | |
return upper_band, lower_band | |
# If Submit button is clicked | |
if button: | |
if not ticker.strip(): | |
st.error("Please provide a valid stock ticker.") | |
elif not google_api_key.strip(): | |
st.error("Please provide a valid Google API Key.") | |
else: | |
try: | |
with st.spinner('Please wait...'): | |
# Retrieve stock data | |
stock = yf.Ticker(ticker) | |
info = stock.info | |
st.subheader(f"{ticker} - {info.get('longName', 'N/A')}") | |
# Plot historical stock price data | |
if period == "1D": | |
history = stock.history(period="1d", interval="1h") | |
elif period == "5D": | |
history = stock.history(period="5d", interval="1d") | |
elif period == "1M": | |
history = stock.history(period="1mo", interval="1d") | |
elif period == "6M": | |
history = stock.history(period="6mo", interval="1wk") | |
elif period == "YTD": | |
history = stock.history(period="ytd", interval="1mo") | |
elif period == "1Y": | |
history = stock.history(period="1y", interval="1mo") | |
elif period == "5Y": | |
history = stock.history(period="5y", interval="3mo") | |
# Create a plotly figure | |
fig = go.Figure() | |
fig.add_trace(go.Scatter(x=history.index, y=history['Close'], mode='lines', name='Close Price')) | |
# Add Technical Indicators | |
if sma_checkbox: | |
sma = calculate_sma(history['Close'], window=20) | |
fig.add_trace(go.Scatter(x=history.index, y=sma, mode='lines', name='SMA (20)')) | |
if ema_checkbox: | |
ema = calculate_ema(history['Close'], window=20) | |
fig.add_trace(go.Scatter(x=history.index, y=ema, mode='lines', name='EMA (20)')) | |
if rsi_checkbox: | |
rsi = calculate_rsi(history['Close'], window=14) | |
fig.add_trace(go.Scatter(x=history.index, y=rsi, mode='lines', name='RSI (14)', yaxis='y2')) | |
fig.update_layout(yaxis2=dict(title='RSI', overlaying='y', side='right')) | |
if macd_checkbox: | |
macd, signal = calculate_macd(history['Close']) | |
fig.add_trace(go.Scatter(x=history.index, y=macd, mode='lines', name='MACD')) | |
fig.add_trace(go.Scatter(x=history.index, y=signal, mode='lines', name='Signal Line')) | |
if bollinger_checkbox: | |
upper_band, lower_band = calculate_bollinger_bands(history['Close'], window=20) | |
fig.add_trace(go.Scatter(x=history.index, y=upper_band, mode='lines', name='Upper Band')) | |
fig.add_trace(go.Scatter(x=history.index, y=lower_band, mode='lines', name='Lower Band')) | |
fig.update_layout( | |
title=f"Historical Stock Prices for {ticker}", | |
xaxis_title="Date", | |
yaxis_title="Close Price", | |
hovermode="x unified" | |
) | |
st.plotly_chart(fig, use_container_width=True) | |
col1, col2, col3 = st.columns(3) | |
# Display stock information as a dataframe | |
country = info.get('country', 'N/A') | |
sector = info.get('sector', 'N/A') | |
industry = info.get('industry', 'N/A') | |
market_cap = info.get('marketCap', 'N/A') | |
ent_value = info.get('enterpriseValue', 'N/A') | |
employees = info.get('fullTimeEmployees', 'N/A') | |
stock_info = [ | |
("Stock Info", "Value"), | |
("Country ", country), | |
("Sector ", sector), | |
("Industry ", industry), | |
("Market Cap ", format_value(market_cap)), | |
("Enterprise Value ", format_value(ent_value)), | |
("Employees ", employees) | |
] | |
df = pd.DataFrame(stock_info[1:], columns=stock_info[0]) | |
col1.dataframe(df, width=400, hide_index=True) | |
# Display price information as a dataframe | |
current_price = info.get('currentPrice', 'N/A') | |
prev_close = info.get('previousClose', 'N/A') | |
day_high = info.get('dayHigh', 'N/A') | |
day_low = info.get('dayLow', 'N/A') | |
ft_week_high = info.get('fiftyTwoWeekHigh', 'N/A') | |
ft_week_low = info.get('fiftyTwoWeekLow', 'N/A') | |
price_info = [ | |
("Price Info", "Value"), | |
("Current Price ", f"${current_price:.2f}"), | |
("Previous Close ", f"${prev_close:.2f}"), | |
("Day High ", f"${day_high:.2f}"), | |
("Day Low ", f"${day_low:.2f}"), | |
("52 Week High ", f"${ft_week_high:.2f}"), | |
("52 Week Low ", f"${ft_week_low:.2f}") | |
] | |
df = pd.DataFrame(price_info[1:], columns=price_info[0]) | |
col2.dataframe(df, width=400, hide_index=True) | |
# Display business metrics as a dataframe | |
forward_eps = info.get('forwardEps', 'N/A') | |
forward_pe = info.get('forwardPE', 'N/A') | |
peg_ratio = info.get('pegRatio', 'N/A') | |
dividend_rate = info.get('dividendRate', 'N/A') | |
dividend_yield = info.get('dividendYield', 'N/A') | |
recommendation = info.get('recommendationKey', 'N/A') | |
biz_metrics = [ | |
("Business Metrics", "Value"), | |
("EPS (FWD) ", f"{forward_eps:.2f}"), | |
("P/E (FWD) ", f"{forward_pe:.2f}"), | |
("PEG Ratio ", f"{peg_ratio:.2f}"), | |
("Div Rate (FWD) ", f"${dividend_rate:.2f}"), | |
("Div Yield (FWD) ", f"{dividend_yield * 100:.2f}%"), | |
("Recommendation ", recommendation.capitalize()) | |
] | |
df = pd.DataFrame(biz_metrics[1:], columns=biz_metrics[0]) | |
col3.dataframe(df, width=400, hide_index=True) | |
# Forecasting | |
st.subheader("Stock Price Forecast ๐ฎ") | |
df_forecast = history.reset_index()[['Date', 'Close']] | |
df_forecast['Date'] = pd.to_datetime(df_forecast['Date']).dt.tz_localize(None) # Remove timezone information | |
df_forecast.columns = ['ds', 'y'] | |
m = Prophet(daily_seasonality=True) | |
m.fit(df_forecast) | |
future = m.make_future_dataframe(periods=forecast_period) | |
forecast = m.predict(future) | |
fig2 = go.Figure() | |
fig2.add_trace(go.Scatter(x=forecast['ds'], y=forecast['yhat'], mode='lines', name='Forecast')) | |
fig2.add_trace(go.Scatter(x=forecast['ds'], y=forecast['yhat_upper'], mode='lines', name='Upper Confidence Interval', line=dict(dash='dash'))) | |
fig2.add_trace(go.Scatter(x=forecast['ds'], y=forecast['yhat_lower'], mode='lines', name='Lower Confidence Interval', line=dict(dash='dash'))) | |
fig2.update_layout( | |
title=f"Stock Price Forecast for {ticker}", | |
xaxis_title="Date", | |
yaxis_title="Predicted Close Price", | |
hovermode="x unified" | |
) | |
st.plotly_chart(fig2, use_container_width=True) | |
# Generate reasons based on forecast | |
graph_description = f"The stock price forecast graph for {ticker} shows the predicted close prices along with the upper and lower confidence intervals for the next {forecast_period} days." | |
reasons = generate_reasons(fig, stock_info, price_info, biz_metrics, google_api_key) | |
st.subheader("Investment Analysis") | |
st.write(reasons) | |
except Exception as e: | |
st.exception(f"An error occurred: {e}") | |