Pour l'instant fait pas grand chose
Project description
Forecastor for Buildings' Consumption
Go check ce lien pour rédiger le README: Github-flavored Markdown
1. Choses à faire
- FAUT MODIFIER LE SETUP.PY? VOILA VOILA
- Ajouter des features
- Gérer les exceptions un peu partout pour que ce soit user friendly *_* (simley avec des étoiles dans les yeux)
- Ajouter un modele (voir 2 ou 3 soyons fous)
- comprendre plus encore le sujet mdr
2. Features' List for preprocessing data
- day_of_week(date_serie): Input: serie of dates ; Output: serie of corresponding week days (['Monday', 'Tuesday', ...])
- cycle_time(df): From the 3rd competitor of the Forecast challenge by Schneider Electric ; turns time in a continous element (no break between 23h59 and 00h01) by applying cosinus and sinus functions
- add_weather(df, weather_df): From the 3rd competitor of the Forecast challenge by Schneider Electric ; add the weather data to the training dataset (df here) merging the two dataframes on the 'Timestamp'
3. Requirements for dataframes
- The column containing dates must be labeled 'Timestamp'
4. Model functions
- building_regressor(): returns a linear regressor from Scikit-learn
- building_train(reg, X, y): train the regressor with X the data and Y the targeted values
- building_prediction(reg, X): returns a dataframe showing the prediction of the regressor reg given the data X
5. To install the package
- Command: python -m pip install --index-url https://test.pypi.org/simple/ --no-deps building_energy_forecastor
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for building_energy_forecastor-0.0.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8273e7acae2a80407f7f11b213f22c237c41456e980767016e03a85320bb88ab |
|
MD5 | 0f9842beb78da3e61ffaeb4dccbf110c |
|
BLAKE2b-256 | f0ac3bac7b58e2cbb5cbaf8970b2e3809929107320f45a4507eab44a62307627 |
Close
Hashes for building_energy_forecastor-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 0f15223f9e91f122a994f992fd18bf971d3f8a1d3b65a66922be8c78f19dae3f |
|
MD5 | 2e54e6573ea85b936b89d9d07932ea67 |
|
BLAKE2b-256 | 5965ddd0a127993a7e9cb03b33456fd6855f94aa29e00bae0014e11e82273974 |