squeeze_v2

import pandas as pd
import os
import plotly.graph_objects as go
import yfinance as yf

dataframes = {}

# Define in squeeze function
def in_squeeze(row):
    return row['lower_band'] > row['lower_KC'] and row['upper_band'] < row['upper_KC']

# Loop through each file in the datasets directory
for filename in os.listdir('datasets'):
    symbol = filename.split(".")[0]  # Extract the symbol from the filename

    # Read the CSV file into a DataFrame
    df = pd.read_csv(f'datasets/{filename}')

    # Check if DataFrame is empty
    if df.empty:
        print(f"No data found in {filename}. Skipping...")
        continue

    # Convert relevant columns to numeric, handling errors
    try:
        df["Open"] = pd.to_numeric(df["Open"], errors='coerce')
        df["Close"] = pd.to_numeric(df["Close"], errors='coerce')
        df["High"] = pd.to_numeric(df["High"], errors='coerce')
        df["Low"] = pd.to_numeric(df["Low"], errors='coerce')
    except KeyError as e:
        print(f"KeyError: {e}. Check if the column exists in {filename}.")
        continue

    # Rename columns only if they match expected length
    current_columns_count = df.shape[1]
    if current_columns_count == 6:  # Adjust this based on your actual data structure
        df.columns = ["Date", "Close", "High", "Low", "Open", "Volume"]
        df.drop(index=[0, 1], inplace=True)  # Adjust this if necessary
        df["Date"] = pd.to_datetime(df["Date"])

        # Calculate Bollinger Bands, Keltner Channels, Stadndard Deviation, Average True Range and SMA
        df["20sma"] = df['Close'].rolling(window=20).mean()
        df['stddev'] = df['Close'].rolling(window=20).std()
        df['upper_band'] = df['20sma'] + 2 * df['stddev']
        df['lower_band'] = df['20sma'] - 2 * df['stddev']
        df['TR'] = abs(df['High']-df['Low'])
        df['ATR'] = df['TR'].rolling(window=20).mean()
        df['upper_KC'] = df['20sma'] + (df['ATR'] * 1.5)
        df['lower_KC'] = df['20sma'] - (df['ATR'] * 1.5)

        df["squeeze_on"]=df.apply(in_squeeze, axis = 1)

        if len(df) >= 2 and not df.iloc[-1]['squeeze_on'] and df.iloc[-2]['squeeze_on']:

                print(f"{symbol} has started squeezing")
                dataframes[symbol] = df


#Create a candlestick chart using Plotly
def chart(df):
    # Define settings for plotly
    candlestick = go.Candlestick(x=df["Date"], open=df["Open"], high=df["High"], low=df["Low"], close=df["Close"])
    upper_band = go.Scatter(x=df["Date"], y=df["upper_band"], name='Upper Bollinger Band', line={'color': 'red'})
    lower_band = go.Scatter(x=df["Date"], y=df["lower_band"], name='Lower Bollinger Band', line={'color': 'blue'})
    upper_KC = go.Scatter(x=df["Date"], y=df["upper_KC"], name='Upper Keltner Channel', line={'color': 'purple'})
    lower_KC = go.Scatter(x=df["Date"], y=df["lower_KC"], name='Lower Keltner Channel', line={'color': 'green'})

    fig = go.Figure(data=[candlestick, upper_band, lower_band, upper_KC, lower_KC])
    fig.layout.xaxis.type='category'
    fig.layout.xaxis.rangeslider.visible= False

    fig.show()

for symbol, df in dataframes.items():
    chart(df)