bukosabino / ta

Technical Analysis Library in Python It is a Technical Analysis library useful to do feature engineering from financial time series datasets (Open, Close, High, Low, Volume). It is built on Pandas and Numpy. The library has implemented 43 indicators: Volume ID | Name | Class | defs -- |-- |-- |-- | 1 | Money Flow Index (MFI) | MFIIndicator | money_flow_index 2 | Accumulation/Distribution Index (ADI) | AccDistIndexIndicator | acc_dist_index 3 | On-Balance Volume (OBV) | OnBalanceVolumeIndicator | on_balance_volume 4 | Chaikin Money Flow (CMF) | ChaikinMoneyFlowIndicator | chaikin_money_flow 5 | Force Index (FI) | ForceIndexIndicator | force_index 6 | Ease of Movement (EoM, EMV) | EaseOfMovementIndicator | ease_of_movement sma_ease_of_movement 7 | Volume-price Trend (VPT) | VolumePriceTrendIndicator| volume_price_trend 8 | Negative Volume Index (NVI) | NegativeVolumeIndexIndicator| negative_volume_index 9 | Volume Weighted Average Price (VWAP) | VolumeWeightedAveragePrice | volume_weighted_average_price Volatility ID | Name | Class | defs -- |-- |-- |-- | 10 | Average True Range (ATR) | AverageTrueRange | average_true_range 11 | Bollinger Bands (BB) | BollingerBands | bollinger_hband bollinger_hband_indicator bollinger_lband bollinger_lband_indicator bollinger_mavg bollinger_pband bollinger_wband 12 | Keltner Channel (KC) | KeltnerChannel | keltner_channel_hband keltner_channel_hband_indicator keltner_channel_lband keltner_channel_lband_indicator keltner_channel_mband keltner_channel_pband keltner_channel_wband 13 | Donchian Channel (DC) | DonchianChannel| donchian_channel_hband donchian_channel_lband donchian_channel_mban donchian_channel_pband donchian_channel_wband 14 | Ulcer Index (UI) | UlcerIndex| ulcer_index Trend ID | Name | Class | defs -- |-- |-- |-- | 15 | Simple Moving Average (SMA) | SMAIndicator | sma_indicator 16 | Exponential Moving Average (EMA) | EMAIndicator | ema_indicator | Trend 17 | Weighted Moving Average (WMA) | WMAIndicator | wma_indicator 18 | Moving Average Convergence Divergence (MACD) | MACD | macd macd_diff macd_signal 19 | Average Directional Movement Index (ADX) | ADXIndicator | adx adx_neg adx_pos 20 | Vortex Indicator (VI) | VortexIndicator | vortex_indicator_neg vortex_indicator_pos 21 | Trix (TRIX) | TRIXIndicator | trix 22 | Mass Index (MI) | MassIndex | mass_index 23 | Commodity Channel Index (CCI) | CCIIndicator| cci 24 | Detrended Price Oscillator (DPO) | DPOIndicator | dpo 25 | KST Oscillator (KST) | KSTIndicator | kst kst_sig 26 | Ichimoku Kinkō Hyō (Ichimoku) | IchimokuIndicator | ichimoku_a ichimoku_b ichimoku_base_line ichimoku_conversion_line 27 | Parabolic Stop And Reverse (Parabolic SAR) | PSARIndicator | psar_down psar_down_indicator psar_up psar_up_indicator 28 | Schaff Trend Cycle (STC) | STCIndicator | stc 29 | Aroon Indicator | AroonIndicator | aroon_down aroon_up Momentum ID | Name | Class | defs -- |-- |-- |-- | 30 | Relative Strength Index (RSI) | RSIIndicator | rsi 31 | Stochastic RSI (SRSI) | StochRSIIndicator | stochrsi stochrsi_d stochrsi_k 32 | True strength index (TSI) | TSIIndicator | tsi 33 | Ultimate Oscillator (UO) | UltimateOscillator | ultimate_oscillator 34 | Stochastic Oscillator (SR) | StochasticOscillator | stoch stoch_signal 35 | Williams %R (WR) | WilliamsRIndicator | williams_r 36 | Awesome Oscillator (AO) | AwesomeOscillatorIndicator | awesome_oscillator 37 | Kaufman's Adaptive Moving Average (KAMA) | KAMAIndicator | kama 38 | Rate of Change (ROC) | ROCIndicator | roc 39 | Percentage Price Oscillator (PPO) | PercentagePriceOscillator | ppo ppo_hist ppo_signal 40 | Percentage Volume Oscillator (PVO) | PercentageVolumeOscillator | pvo pvo_hist pvo_signal Others ID | Name | Class | defs -- |-- |-- |-- | 41 | Daily Return (DR) | DailyReturnIndicator | daily_return 42 | Daily Log Return (DLR) | DailyLogReturnIndicator | daily_log_return 43 | Cumulative Return (CR) | CumulativeReturnIndicator | cumulative_return Documentation https://technical-analysis-library-in-python.readthedocs.io/en/latest/ Motivation to use • English • Spanish How to use (Python 3) To use this library you should have a financial time series dataset including , , , , and columns. You should clean or fill NaN values in your dataset before add technical analysis features. You can get code examples in examples_to_use folder. You can visualize the features in this notebook. Example adding all features Example adding particular feature `python import pandas as pd from ta.utils import dropna from ta.volatility import BollingerBands Load datas df = pd.read_csv('ta/tests/data/datas.csv', sep=',') Clean NaN values df = dropna(df) Initialize Bollinger Bands Indicator indicator_bb = BollingerBands(close=df["Close"], window=20, window_dev=2) Add Bollinger Bands fe _...truncated for preview_