vanbrands

from sklearn.preprocessing import KBinsDiscretizer
from sklearn.model_selection import RandomizedSearchCV

search_space = {
  'preprocessing__binfeatures__n_bins': [10, 20],
  'model__n_estimators': [500, 1000, 2000],
  'model__class_weight': ['balanced', 'balanced_subsample']
}

preprocessing = ColumnTransformer(transformers=[

vanbrands

# Persist pipeline to disk
pipeline.fit(x_train, y_train)
joblib.dump(pipeline, 'model.joblib')

# Load pipeline and make prediction
pipeline = joblib.load('model.joblib')
y_hat = pipeline.predict(x)

vanbrands

from sklearn.compose import ColumnTransformer

# Define you transformers.
preprocessing = ColumnTransformer(transformers=[
    ('encode_categorical_features', OneHotEncoder(), ['categorical_column'])
], remainder='passthrough')

estimator = GradientBoostingClassifier()

# Define steps in the pipeline.

vanbrands

from sklearn.preprocessing import OneHotEncoder

encoder = OneHotEncoder()
dummies = encoder.fit_transform(df['categorical_column'])

vanbrands

# You have you set of possible categories in a list for example.
# (it could be anything really...)
possible_categories = ['foo', 'bar]

# Convert the categorical column to type Categorical
df['categorical_column'] = pd.Categorical(
  values=df['categorical_column'],
  categories=possible_categories
)
                       

vanbrands

import pandas as pd

dummies = pd.get_dummies(df, columns=['categorical_colum1', 'categorical_colum2'])

vanbrands

dummies = pd.get_dummies(df['categorical_column'])

vanbrands

aws cloudformation deploy /
  --template-file cloudformation_notebook.yaml /
  --stack-name notebook-tutorial

vanbrands

AWSTemplateFormatVersion: '2010-09-09'
Description: 'Cloudformation simples para subir um notebook no Sagemaker'
Resources:
  NotebookTutorial:
    Type: AWS::SageMaker::NotebookInstance
    Properties: 
      NotebookInstanceName: "Notebook Tutorial"
      InstanceType: ml.t2.medium
      RoleArn: String
      VolumeSizeInGB: 20

vanbrands

select tab.table_schema,
       tab.table_name,
       tinf.tbl_rows as rows
from svv_tables tab
join svv_table_info tinf
          on tab.table_schema = tinf.schema
          and tab.table_name = tinf.table
where tab.table_type = 'BASE TABLE'
      and tab.table_schema not in('pg_catalog','information_schema')
      and tinf.tbl_rows > 1