Create app.py

app.py

@@ -0,0 +1,122 @@
+import yfinance as yf
+import pandas as pd
+import numpy as np
+import plotly.graph_objects as go
+from plotly.subplots import make_subplots
+import streamlit as st
+
+# Helper function to fetch stock data
+def fetch_stock_data(ticker: str, start_date: str, end_date: str) -> pd.DataFrame:
+    """Fetch stock data from Yahoo Finance."""
+    return yf.download(ticker, start=start_date, end=end_date)
+
+# Function to estimate probability and plot
+def estimate_probability(data, n_days, initial_price, up_target, down_target):
+    # Calculate the thresholds for price change
+    up_threshold = round(abs((up_target - initial_price) / initial_price), 3)
+    down_threshold = round(abs((down_target - initial_price) / initial_price), 3)
+
+    # Calculate the n-day percentage change
+    data[f'{n_days}d_pct_change'] = data['Adj Close'].pct_change(n_days)
+
+    # Calculate the frequency of the threshold price change
+    total_periods = len(data)
+    down_periods = len(data[data[f'{n_days}d_pct_change'] <= -down_threshold])
+    up_periods = len(data[data[f'{n_days}d_pct_change'] >= up_threshold])
+    down_frequency = down_periods / total_periods
+    up_frequency = up_periods / total_periods
+
+    # Plotting
+    fig = make_subplots(rows=2, cols=1, shared_xaxes=True, vertical_spacing=0.1,
+                        subplot_titles=(f'Distribution of {n_days}-day percentage changes', f'Stock Price for {ticker}'),
+                        specs=[[{"secondary_y": False}], [{"secondary_y": False}]])
+
+    fig.add_trace(go.Histogram(x=data[f'{n_days}d_pct_change'], nbinsx=100, name='Percentage Change'), row=1, col=1)
+    fig.add_vline(x=-down_threshold, line=dict(color='red', dash='dash'), annotation_text=f"{down_threshold * 100:.2f}% decrease frequency: {down_frequency * 100:.2f}%", annotation_position="bottom left", row=1, col=1)
+    fig.add_vline(x=up_threshold, line=dict(color='blue', dash='dash'), annotation_text=f"{up_threshold * 100:.2f}% increase frequency: {up_frequency * 100:.2f}%", annotation_position="top right", row=1, col=1)
+
+    fig.add_trace(go.Scatter(x=data.index, y=data['Adj Close'], mode='lines', name='Adjusted Close Price'), row=2, col=1)
+    up_instances = data[data[f'{n_days}d_pct_change'] >= up_threshold]
+    down_instances = data[data[f'{n_days}d_pct_change'] <= -down_threshold]
+    fig.add_trace(go.Scatter(x=up_instances.index, y=up_instances['Adj Close'], mode='markers', marker=dict(color='blue', symbol='triangle-up', size=10), name=f"{up_threshold * 100:.2f}% increase"), row=2, col=1)
+    fig.add_trace(go.Scatter(x=down_instances.index, y=down_instances['Adj Close'], mode='markers', marker=dict(color='red', symbol='triangle-down', size=10), name=f"{down_threshold * 100:.2f}% decrease"), row=2, col=1)
+
+    fig.update_layout(title_text=f"Probability Estimation and Stock Price for {ticker}", xaxis_title='Date', yaxis_title='Adjusted Close Price')
+
+    return fig, up_frequency, down_frequency
+
+# Streamlit app
+st.set_page_config(page_title="Stock Probability Analysis", layout="wide")
+st.title('Stock Probability Analysis')
+
+# Sidebar for method selection
+st.sidebar.header("Input Parameters")
+ticker = st.sidebar.text_input('Enter Stock Ticker', 'SAP.DE')
+start_date = st.sidebar.date_input('Start Date', pd.to_datetime('2020-01-01'))
+end_date = st.sidebar.date_input('End Date', pd.to_datetime('2025-12-02'))
+
+# Fetch data to set default values
+if 'data' not in st.session_state:
+    st.session_state.data = fetch_stock_data(ticker, start_date, end_date)
+data = st.session_state.data
+
+# Set default values
+default_initial_price = data['Adj Close'].iloc[-1]
+default_up_target = default_initial_price + 10
+default_down_target = default_initial_price - 10
+
+# Sidebar for dynamic inputs
+n_days = st.sidebar.slider('Number of Days', min_value=1, max_value=100, value=30, step=1)
+initial_price = st.sidebar.number_input('Initial Price', value=default_initial_price)
+up_target = st.sidebar.number_input('Up Target', value=default_up_target)
+down_target = st.sidebar.number_input('Down Target', value=default_down_target)
+
+# Explanation and instructions
+st.markdown("""
+### How to Use
+
+1. **Enter Stock Ticker**: Input the stock symbol you want to analyze.
+2. **Select Date Range**: Choose the start and end dates for the historical data.
+3. **Set Parameters**:
+   - **Number of Days (n_days)**: Define the period over which you want to calculate the percentage change.
+   - **Initial Price**: The starting price for your analysis.
+   - **Up Target**: The target price for an upward move.
+   - **Down Target**: The target price for a downward move.
+4. **Run Analysis**: Click the 'Run Analysis' button to generate the results.
+
+### Explanation of the Analysis
+
+This app estimates the probability of a stock reaching certain price targets within a specified number of days based on historical data.
+
+- **Distribution of Percentage Changes**: The histogram shows the distribution of percentage changes over the selected number of days.
+- **Price Targets**: The vertical lines indicate the price targets for upward and downward moves. The frequencies of reaching these targets are annotated.
+- **Stock Price Plot**: The line chart shows the historical adjusted close prices with markers indicating instances where the price targets were met.
+""")
+
+# Run button
+run_button = st.sidebar.button('Run Analysis')
+
+# Fetch data and display results
+if run_button:
+    st.session_state.data = fetch_stock_data(ticker, start_date, end_date)
+    data = st.session_state.data
+
+    if initial_price == 0.0:
+        initial_price = data['Adj Close'].iloc[-1]
+    if up_target == 0.0:
+        up_target = initial_price + 10
+    if down_target == 0.0:
+        down_target = initial_price - 10
+
+    fig, up_frequency, down_frequency = estimate_probability(data, n_days, initial_price, up_target, down_target)
+    st.plotly_chart(fig)
+
+    st.markdown(f"""
+    ### Results
+
+    **Probability of Reaching Targets:**
+    - Probability of reaching the up target ({up_target:.2f}) in {n_days} days: **{up_frequency * 100:.2f}%**
+    - Probability of reaching the down target ({down_target:.2f}) in {n_days} days: **{down_frequency * 100:.2f}%**
+
+    This analysis helps in understanding the historical likelihood of the stock price reaching certain targets within a specified number of days.
+    """)