# Install
```
pip install auger.ai.predict
```
# Auger.ai.predict
Auger ML predict Python API and command line interface
# Download exported model
To download exported model you can use:
- Auger.ai web : https://app.auger.ai
- auger.ai command line interface: https://pypi.org/project/auger.ai/
# Predict using exported model
- Unzip file with model
- Run client.py from model folder:
python <model_path>/client.py --path_to_predict <data_path> --model_path model_path
--path_to_predict - path to file with data to predict. Should contain features used to train model
--model_path - folder which contain model.pkl.gz file
For example:
python ./models/export_9BB0BFA3D368454/client.py --path_to_predict ./files/baseball_predict.csv --model_path ./models/export_9BB0BFA3D368454/model
## Client.py command line parameters
--path_to_predict Path to file for predict
--model_path Path to folder with model
--threshold Threshold to use for calculate target using predict_proba
--score 0/1 Build scores after prediction if prediction data contain actual target
# Auger.ai.predict Python API
## auger_ml.model_exporter.ModelExporter
ModelExporter provides interface to Auger predict API.
- **ModelExporter(options)** - constructs ModelExporter instance.
- options - optional parameters. Must be {} for now
- **predict_by_model(model_path, path_to_predict=None, records=None, features=None, threshold=None)** - produce prediction based on exported model and data
- model_path - folder which contain model.pkl.gz file
- path_to_predict - data to predict
- records - data to predict: list of lists. path_to_predict should be None in this case. For example: [[0.1,0.2],[0.1, 0.3]]
- features - feature names for records. Used only when records is not None
- threshold - set threshold to produce prediction for classification based on probabilities. proba_ column will be added to prediction result for each target class
- RETURN: predictions - if path_to_predict is not None, then file in same directory with predcitions, or pandas dataframe
Example:
```
def predict_by_model_example(path_to_predict=None, threshold=None, model_path=None):
#features is an array mapping your data to the feature, your feature and data should be
#the same that you trained your model with.
#If it is None, features read from model/options.json file
#['feature1', 'feature2']
features = None
# data is an array of arrays to get predictions for, input your data below
# each record should contain values for each feature
records = [[],[]]
if path_to_predict:
path_to_predict=os.path.abspath(path_to_predict)
predictions = ModelExporter({}).predict_by_model(
records=records,
model_path=model_path,
path_to_predict=path_to_predict,
features=features,
threshold=threshold
)
return predictions
```
- **load_model(model_path)** - load model from file.
- model_path - folder which contain model.pkl.gz file
- RETURN: model, timeseries_model
- model - ML model to call predict
- timeseries_model - flag is this timeseries model or not
- **preprocess_data(model_path, data_path, records=None, features=None)** - preprocess data for predict. It will process data same way as train data used for model
- model_path - folder which contain model.pkl.gz file
- data_path - data to preprocess
- records - data to predict: list of lists. data_path should be None in this case. For example: [[0.1,0.2],[0.1, 0.3]]
- features - feature names for records. Used only when records is not None
- RETURN: X_test, Y_test, target_categoricals
- X_test - data to call predict
- Y_test - array with target values
- target_categoricals - dict with categories for target, may be used to get actual target values
Example:
```
def predict_by_model_example(path_to_predict=None, model_path=None):
model_exporter = ModelExporter({})
model, timeseries_model = model_exporter.load_model(model_path)
X_test, Y_test, target_categoricals = model_exporter.preprocess_data(model_path,
data_path=path_to_predict)
results = model.predict(X_test)
# If your target is categorical you can translate predicted values back to original:
# target_feature = "target"
# categories = target_categoricals[target_feature]['categories']
# results = map(lambda x: categories[int(x)], results)
```
Example for timeseries data:
```
def predict_by_model_timeseries_example(path_to_predict=None, model_path=None):
model_exporter = ModelExporter({})
model, timeseries_model = model_exporter.load_model(model_path)
X_test, Y_test, target_categoricals = model_exporter.preprocess_data(model_path,
data_path=path_to_predict)
if timeseries_model:
results = model.predict((X_test, Y_test, False))[-1:]
else:
results = model.predict(X_test.iloc[-1:])
```
Raw data
{
"_id": null,
"home_page": "https://github.com/deeplearninc/auger-ai",
"name": "auger.ai.predict",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3",
"maintainer_email": "",
"keywords": "augerai auger ai machine learning automl deeplearn api sdk prediction predict",
"author": "Deep Learn, Inc.",
"author_email": "augerai@dplrn.com",
"download_url": "",
"platform": "any",
"description": "# Install\n```\npip install auger.ai.predict\n```\n\n# Auger.ai.predict\nAuger ML predict Python API and command line interface\n\n\n# Download exported model\n\nTo download exported model you can use:\n\n- Auger.ai web : https://app.auger.ai\n- auger.ai command line interface: https://pypi.org/project/auger.ai/\n\n# Predict using exported model\n\n- Unzip file with model\n- Run client.py from model folder:\n\npython <model_path>/client.py --path_to_predict <data_path> --model_path model_path\n\n--path_to_predict - path to file with data to predict. Should contain features used to train model\n--model_path - folder which contain model.pkl.gz file\n\nFor example:\n\npython ./models/export_9BB0BFA3D368454/client.py --path_to_predict ./files/baseball_predict.csv --model_path ./models/export_9BB0BFA3D368454/model\n\n## Client.py command line parameters\n\n --path_to_predict Path to file for predict\n\n --model_path Path to folder with model\n\n --threshold Threshold to use for calculate target using predict_proba\n\n --score 0/1 Build scores after prediction if prediction data contain actual target\n\n# Auger.ai.predict Python API\n## auger_ml.model_exporter.ModelExporter\nModelExporter provides interface to Auger predict API.\n\n- **ModelExporter(options)** - constructs ModelExporter instance.\n - options - optional parameters. Must be {} for now\n\n- **predict_by_model(model_path, path_to_predict=None, records=None, features=None, threshold=None)** - produce prediction based on exported model and data\n - model_path - folder which contain model.pkl.gz file\n - path_to_predict - data to predict\n - records - data to predict: list of lists. path_to_predict should be None in this case. For example: [[0.1,0.2],[0.1, 0.3]]\n - features - feature names for records. Used only when records is not None\n - threshold - set threshold to produce prediction for classification based on probabilities. proba_ column will be added to prediction result for each target class\n\n - RETURN: predictions - if path_to_predict is not None, then file in same directory with predcitions, or pandas dataframe\n\n Example:\n ```\n def predict_by_model_example(path_to_predict=None, threshold=None, model_path=None):\n #features is an array mapping your data to the feature, your feature and data should be\n #the same that you trained your model with.\n #If it is None, features read from model/options.json file\n #['feature1', 'feature2']\n features = None \n\n # data is an array of arrays to get predictions for, input your data below\n # each record should contain values for each feature\n records = [[],[]]\n\n if path_to_predict:\n path_to_predict=os.path.abspath(path_to_predict)\n\n predictions = ModelExporter({}).predict_by_model(\n records=records,\n model_path=model_path,\n path_to_predict=path_to_predict,\n features=features,\n threshold=threshold\n )\n\n return predictions\n ```\n\n- **load_model(model_path)** - load model from file.\n - model_path - folder which contain model.pkl.gz file\n\n - RETURN: model, timeseries_model\n - model - ML model to call predict \n - timeseries_model - flag is this timeseries model or not\n\n- **preprocess_data(model_path, data_path, records=None, features=None)** - preprocess data for predict. It will process data same way as train data used for model\n - model_path - folder which contain model.pkl.gz file\n - data_path - data to preprocess\n - records - data to predict: list of lists. data_path should be None in this case. For example: [[0.1,0.2],[0.1, 0.3]]\n - features - feature names for records. Used only when records is not None\n\n - RETURN: X_test, Y_test, target_categoricals\n - X_test - data to call predict \n - Y_test - array with target values\n - target_categoricals - dict with categories for target, may be used to get actual target values\n\n Example:\n ```\n def predict_by_model_example(path_to_predict=None, model_path=None):\n model_exporter = ModelExporter({})\n model, timeseries_model = model_exporter.load_model(model_path)\n X_test, Y_test, target_categoricals = model_exporter.preprocess_data(model_path, \n data_path=path_to_predict)\n\n results = model.predict(X_test)\n\n # If your target is categorical you can translate predicted values back to original:\n # target_feature = \"target\"\n # categories = target_categoricals[target_feature]['categories']\n # results = map(lambda x: categories[int(x)], results)\n ```\n\n Example for timeseries data:\n ```\n def predict_by_model_timeseries_example(path_to_predict=None, model_path=None):\n model_exporter = ModelExporter({})\n model, timeseries_model = model_exporter.load_model(model_path)\n X_test, Y_test, target_categoricals = model_exporter.preprocess_data(model_path, \n data_path=path_to_predict)\n\n if timeseries_model:\n results = model.predict((X_test, Y_test, False))[-1:]\n else:\n results = model.predict(X_test.iloc[-1:])\n ```\n\n\n",
"bugtrack_url": null,
"license": "Apache",
"summary": "Auger ML predict python and command line interface",
"version": "1.1.12",
"project_urls": {
"Homepage": "https://github.com/deeplearninc/auger-ai"
},
"split_keywords": [
"augerai",
"auger",
"ai",
"machine",
"learning",
"automl",
"deeplearn",
"api",
"sdk",
"prediction",
"predict"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "de5f3b399fc5b92d7b534d95c05c5db362e1cad938b67f8dd0f138519564edb5",
"md5": "c76864473be2a06d7d497cd80b8fdb29",
"sha256": "b6d0520145834104fbf3e2846c6567aa0b7485fd5d6ea7d49e007c54ec3746bc"
},
"downloads": -1,
"filename": "auger.ai.predict-1.1.12-py3-none-any.whl",
"has_sig": false,
"md5_digest": "c76864473be2a06d7d497cd80b8fdb29",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3",
"size": 134519,
"upload_time": "2024-01-20T18:12:29",
"upload_time_iso_8601": "2024-01-20T18:12:29.634075Z",
"url": "https://files.pythonhosted.org/packages/de/5f/3b399fc5b92d7b534d95c05c5db362e1cad938b67f8dd0f138519564edb5/auger.ai.predict-1.1.12-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-01-20 18:12:29",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "deeplearninc",
"github_project": "auger-ai",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"circle": true,
"lcname": "auger.ai.predict"
}
JSON
