The FreqGym_normalized strategy is a trading strategy implemented as a class in Python. It is used to populate indicators, generate buy signals, and generate sell signals for a given DataFrame of trading data. The populate_indicators method adds various technical analysis (TA) indicators to the DataFrame.
These indicators include: PLUS_DI: Calculates the Plus Directional Indicator MINUS_DI: Calculates the Minus Directional Indicator ULTOSC: Calculates the Ultimate Oscillator HT_SINE: Calculates the Hilbert Transform - Sine Wave BOP: Calculates the Balance of Power STOCH: Calculates the Stochastic Oscillator STOCHF: Calculates the Fast Stochastic Oscillator ADX: Calculates the Average Directional Movement Index AROON: Calculates the Aroon Indicator AROONOSC: Calculates the Aroon Oscillator CMO: Calculates the Chande Momentum Oscillator DX: Calculates the Directional Movement Index MFI: Calculates the Money Flow Index WILLR: Calculates the Williams' %R RSI: Calculates the Relative Strength Index STOCHRSI: Calculates the Stochastic RSI LINEARREG_ANGLE: Calculates the Linear Regression Angle After calculating the indicators, they are normalized to a range of 0 to 1.
The populate_buy_trend method generates buy signals based on the TA indicators.
It uses an RL model (not shown in the provided code) to predict the action to take. If the predicted action is 1, it sets the 'buy' column in the DataFrame to 1. The populate_sell_trend method generates sell signals based on the TA indicators. Similar to the populate_buy_trend method, it uses the RL model to predict the action. If the predicted action is 2, it sets the 'sell' column in the DataFrame to 1. The last part of the code segment initializes an output DataFrame and populates it with predicted results using the RL model. It uses a rolling window approach to generate predictions based on the indicators. The normalize function is used to normalize the indicator values within a specific range. Overall, this strategy calculates a variety of TA indicators, normalizes them, generates buy and sell signals based on the indicators using an RL model, and produces an output DataFrame with the predicted results.
These indicators include: PLUS_DI: Calculates the Plus Directional Indicator MINUS_DI: Calculates the Minus Directional Indicator ULTOSC: Calculates the Ultimate Oscillator HT_SINE: Calculates the Hilbert Transform - Sine Wave BOP: Calculates the Balance of Power STOCH: Calculates the Stochastic Oscillator STOCHF: Calculates the Fast Stochastic Oscillator ADX: Calculates the Average Directional Movement Index AROON: Calculates the Aroon Indicator AROONOSC: Calculates the Aroon Oscillator CMO: Calculates the Chande Momentum Oscillator DX: Calculates the Directional Movement Index MFI: Calculates the Money Flow Index WILLR: Calculates the Williams' %R RSI: Calculates the Relative Strength Index STOCHRSI: Calculates the Stochastic RSI LINEARREG_ANGLE: Calculates the Linear Regression Angle After calculating the indicators, they are normalized to a range of 0 to 1.
The populate_buy_trend method generates buy signals based on the TA indicators.
It uses an RL model (not shown in the provided code) to predict the action to take. If the predicted action is 1, it sets the 'buy' column in the DataFrame to 1. The populate_sell_trend method generates sell signals based on the TA indicators. Similar to the populate_buy_trend method, it uses the RL model to predict the action. If the predicted action is 2, it sets the 'sell' column in the DataFrame to 1. The last part of the code segment initializes an output DataFrame and populates it with predicted results using the RL model. It uses a rolling window approach to generate predictions based on the indicators. The normalize function is used to normalize the indicator values within a specific range. Overall, this strategy calculates a variety of TA indicators, normalizes them, generates buy and sell signals based on the indicators using an RL model, and produces an output DataFrame with the predicted results.
stoploss: -0.99 timeframe: 5m hash(sha256): aad1b406a1fa6db166177cfe35032dacfb8f1960875d582e2721d418269f745d indicators: sell htsine plus_di_period willr_period mfi_period close aroonup_period aroondown_period uo dx_period rsi_period aroondown fastk htleadsine slowd date open close high low volume buy sell buy_tag leadsine stochrsi_d_period bb3_lower_gt_close minus_di_period plus_di fastd aroonosc_period cmo_period slowk bb2_lower_gt_close adx_period fisher_rsi_period buy stochrsi_k_period aroonup minus_di lower linangle_period bop sine
Similar Strategies: (based on used indicators)
Strategy: FreqGym_normalized_2, Similarity Score: 86.67%
Strategy: FreqGym_normalized_0, Similarity Score: 84.44%
Strategy: FreqGym_normalized_3, Similarity Score: 84.44%
Strategy: FreqGym_normalized, Similarity Score: 82.22%
last change: 2024-04-28 09:27:32