Skip to main content

A comprehensive Python module for feature engineering, target computation, rolling window modeling, feature selection, and model evaluation, tailored for time-series forecasting and stock price analysis.

Project description

Table of Contents

Introduction

Installation

Code Example: Feature Engineering

Code Example: Target Computation

Full Example with Model Training

Contributions

License

Introduction

This Python module provides a set of functions to streamline feature engineering, target generation, rolling window model training, and model evaluation for time-series data. It is particularly designed for financial data like stock prices, allowing the user to create momentum-based features, moving averages, seasonality features, and more. This tool also provides feature selection utilities and model evaluation metrics like accuracy, precision, recall, and F1 score.

Installation

Before running the code, make sure the following libraries are installed:

pip install numpy pandas ta-lib scikit-learn statsmodels matplotlib seaborn

Usage/Examples

Code Example: Feature Engineering

The function prepare_features generates technical indicators based on stock price data, including momentum, moving averages, Bollinger Bands, and more.

import numpy as np
import pandas as pd
from ta.momentum import RSIIndicator
from ta.volatility import BollingerBands

# Sample input dataframe
data = pd.DataFrame({
    'Close': [100, 102, 101, 105, 107, 109, 108, 110, 111, 113],
    'Volume': [2000, 2100, 2050, 2200, 2300, 2250, 2400, 2500, 2450, 2600]
}, index=pd.date_range('2023-01-01', periods=10))

# Call the feature engineering function
feature_names = prepare_features(data)

print(data[feature_names].head())

Code Example: Target Computation

# Generate target for the given dataframe
target = compute_target(data, SL=1, TP=3, future_periods=3)

print(target)

Full Example with Model Training

# Feature engineering on full dataset
x_train, y_train = feature_engineering(data, 'train', future_periods=3)

# Train a random forest model
rf_model = RandomForestClassifier()
rf_model.fit(x_train, y_train)

# Make predictions
y_pred = rf_model.predict(x_train)

# Evaluate the model
evaluation = model_evaluation(
    labels=y_train,
    predictions=y_pred,
    model=rf_model,
    x=x_train,
    y=y_train
)

print(evaluation)

Contributions

If you'd like to contribute to this project, feel free to submit a pull request or open an issue for any bugs or feature requests.

License

This is free and unencumbered software released into the public domain.

Anyone is free to copy, modify, publish, use, compile, sell, or distribute this software, either in source code form or as a compiled binary, for any purpose, commercial or non-commercial, and by any means.

In jurisdictions that recognize copyright laws, the author or authors of this software dedicate any and all copyright interest in the software to the public domain. We make this dedication for the benefit of the public at large and to the detriment of our heirs and successors. We intend this dedication to be an overt act of relinquishment in perpetuity of all present and future rights to this software under copyright law.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

For more information, please refer to https://unlicense.org

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

machine_learner-0.1.0.tar.gz (13.4 kB view details)

Uploaded Source

Built Distribution

machine_learner-0.1.0-py3-none-any.whl (12.9 kB view details)

Uploaded Python 3

File details

Details for the file machine_learner-0.1.0.tar.gz.

File metadata

  • Download URL: machine_learner-0.1.0.tar.gz
  • Upload date:
  • Size: 13.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.9.20

File hashes

Hashes for machine_learner-0.1.0.tar.gz
Algorithm Hash digest
SHA256 eea145df74a9d2acdb851058450165505e8ec68ff9a1b67aeb5fde9b793510eb
MD5 d24aa5eddeceada3fcafbace30b19ec6
BLAKE2b-256 2607a6dfc6d77e5282a8f376d66f436a996dbda0cfe5060fdfe72ac1a104d38d

See more details on using hashes here.

File details

Details for the file machine_learner-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for machine_learner-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 947de6dead4027e4233e33d185278627d80b45ab1fffbcb756eb3aaba310ae36
MD5 2722e919b6e46f1ac6d1c8748ba863d4
BLAKE2b-256 616444ed79088aec4436b0026acd902497827913ca15c9a23061a93376a4ef91

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page