pycaret

# creating a copy of data
data2 = data.copy()
data2.dropna(axis=0, inplace=True)
data2['Converted'] = data2['Converted'].replace({1 : 'Yes', 0 : 'No'})

# plotly visual
import plotly.express as px

fig = px.scatter(x=data2['Total Time Spent on Website'], y=data2['Asymmetrique Activity Score'], 
                 color = data2['Converted'], template = 'plotly_white', 

pycaret

name: PyCaret AutoML Git Action
on: 
  push :
    branches: [ master ]  
jobs:
  build:
    runs-on: ubuntu-latest
    steps:
      - name: PyCaret AutoML Git Action
        id: model

pycaret

name: "PyCaret AutoML Git Action"
description: "A simple example of AutoML created using PyCaret 2.0"
author: "Moez Ali"
inputs:
  DATASET:
    description: "Dataset for Training"
    required: true
    default: "juice"
  TARGET:
    description: "Name of Target variable"

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 os, ast
import pandas as pd

dataset = os.environ["INPUT_DATASET"]
target = os.environ["INPUT_TARGET"]
usecase = os.environ["INPUT_USECASE"]

dataset_path = "https://raw.githubusercontent.com/" + os.environ["GITHUB_REPOSITORY"] + "/master/" + os.environ["INPUT_DATASET"] + '.csv'
data = pd.read_csv(dataset_path)
data.head()

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

# 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 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)