pycaret

FROM python:3.7-slim

WORKDIR /app

ADD . /app

RUN apt-get update && apt-get install -y libgomp1

RUN pip install --trusted-host pypi.python.org -r requirements.txt

pycaret

# import classification module
from pycaret.classification import *

# init setup
clf1 = setup(data, target = 'name-of-target')

# train logistic regression model
lr = create_model('lr') #lr is the id of the model

# check the model library to see all models

pycaret

# select and finalize the best model in the active run
best_model = automl() #returns the best model based on CV score

# select and finalize the best model based on 'F1' on hold_out set
best_model_holdout = automl(optimize = 'F1', use_holdout = True)

# save model
save_model(model, 'c:/path-to-directory/model-name')

# load model

pycaret

# import libraries
import pandas as pd
import sys

# define command line parameters
data = sys.argv[1]
target = sys.argv[2]

# load data (replace this part with your own script)
from pycaret.datasets import get_data

pycaret

# import classification module
from pycaret.classification import *

# init setup
clf1 = setup(data, target = 'name-of-target', log_experiment = True, experiment_name = 'exp-name-here')

# compare models
best = compare_models()

# start mlflow server on localhost:5000 (when using notebook)

pycaret

# import classification module
from pycaret.classification import *

# init setup
clf1 = setup(data, target = 'name-of-target')

# train a decision tree model
dt = create_model('dt')

# tune hyperparameters of decision tree

pycaret

# Import module
from pycaret.classification import *

# Initialize setup (when using Notebook environment)
clf1 = setup(data, target = 'target-variable')

# Initialize setup (outside of Notebook environment)
clf1 = setup(data, target = 'target-variable', html = False)

# Initialize setup (When using remote execution such as Kaggle / GitHub actions / CI-CD pipelines)

pycaret

# train a catboost model
catboost = create_model('catboost')

# predict on holdout set (when no data is passed)
pred_holdout = predict_model(catboost)

# predict on new dataset
new_data = pd.read_csv('new-data.csv')
pred_new = predict_model(catboost, data = new_data)

pycaret

predict_model(xgboost, probability_threshold=0.2)

pycaret

tuned_lda = tune_model(model='lda', supervised_target='status', estimator='xgboost')