Chaining transformations in scikit pipeline - python

I'm using the scikit pipeline to create a preprocess on a dataset. I have a dataset with four variables: ['monetary', 'frequency1', 'frequency2', 'recency'] and I want to preprocess all but recency. To preprocess, I first want to get the log and then standardize. However, when I get the transformed data from the pipeline, I get 7 columns (3 log, 3 standardize, recency). Is there a way to chain the transformations and so I can get the log and after the log perform standardize and only get a 4 feature dataset?
def create_pipeline(df):
all_but_recency = ['monetary', 'frequency1','frequency2']
# Preprocess
preprocessor = ColumnTransformer(
transformers=[
( 'log', FunctionTransformer(np.log), all_but_recency ),
( 'standardize', preprocessing.StandardScaler(), all_but_recency ) ],
remainder='passthrough')
# Pipeline
estimators = [( 'preprocess', preprocessor )]
pipe = Pipeline(steps=estimators)
print(pipe.set_params().fit_transform(df).shape)
Thanks in advance

You have to apply the FunctionTransformer sequentially. Try this!
def create_pipeline(df):
all_but_recency = ['monetary', 'frequency1','frequency2']
# Preprocess
# Preprocess
preprocessor1 = ColumnTransformer([('log', FunctionTransformer(np.log), all_but_recency)],'passthrough')
preprocessor2 = ColumnTransformer([('standardize', preprocessing.StandardScaler(), all_but_recency)],'passthrough' )
# Pipeline
estimators = [('preprocess1', preprocessor1),('standardize', preprocessor2)]
pipe = Pipeline(steps=estimators)
print(pipe.set_params().fit_transform(df).shape)
working example
from sklearn.datasets import load_iris
import pandas as pd
import numpy as np
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import Normalizer
from sklearn.preprocessing import FunctionTransformer
from sklearn.pipeline import Pipeline
from sklearn import preprocessing
iris = load_iris()
X, y = iris.data, iris.target
df= pd.DataFrame(X,columns = iris.feature_names)
all_but_one = [0,1,2]
# Preprocess
preprocessor1 = ColumnTransformer([('log', FunctionTransformer(np.log), all_but_one)],'passthrough')
preprocessor2 = ColumnTransformer([('standardize', preprocessing.StandardScaler(), all_but_one)],'passthrough' )
# Pipeline
estimators = [('preprocess1', preprocessor1),('scalling', preprocessor2)]
pipe = Pipeline(steps=estimators,)
pipe.fit_transform(df)

Related

Extract feature names after Pipeline usage with ColumnTransformer (sklearn)

I have the following toy code.
I use a pipeline to automatically normalize numerical variables and apply one-hot-encoding to the categorical ones.
I can get the coefficients of the linear regression model easily using pipe['logisticregression'].coef_ but how can I get all the feature names in the right order as this appearing in the coef matrix?
from sklearn.compose import ColumnTransformer
import numpy as np, pandas as pd
from sklearn.compose import make_column_transformer, make_column_selector
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline
from sklearn.model_selection import train_test_split
# data from https://www.kaggle.com/datasets/uciml/adult-census-income
data = pd.read_csv("adult.csv")
data = data.iloc[0:3000,:]
target = "workclass"
y = data[target]
X = data.drop(columns=target)
numerical_columns_selector = make_column_selector(dtype_exclude=object)
categorical_columns_selector = make_column_selector(dtype_include=object)
numerical_columns = numerical_columns_selector(X)
categorical_columns = categorical_columns_selector(X)
ct = ColumnTransformer([ ('onehot', OneHotEncoder(handle_unknown='ignore'), categorical_columns) ,
('std', StandardScaler(), numerical_columns)])
model = LogisticRegression(max_iter=500)
pipe = make_pipeline(ct, model)
data_train, data_test, target_train, target_test = train_test_split(
X, y, random_state=42)
pipe.fit(data_train, target_train)
pipe['logisticregression'].coef_.shape

SkLearn DecisionTree Doesn't Include Numerical Features After Fitting

I'm trying to fit a dataframe with SkLearn DecisionTree with the following code. But I get a error Length of feature_names, 9 does not match number of features, 8. The DecisionTree seems to have only fitted categorical features after transformed by onehotencoding, not the numerical feature. How can I include the numerical feature in the decisiontree model?
import pandas as pd
import numpy as np
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import make_pipeline
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn import tree
from matplotlib import pyplot as plt
import graphviz
import numpy as np
import pandas as pd
from sklearn.preprocessing import OneHotEncoder,StandardScaler
from sklearn.compose import ColumnTransformer, make_column_transformer
from sklearn.linear_model import LinearRegression
df = pd.DataFrame({'brand' : ['aaaa', 'asdfasdf', 'sadfds', 'NaN'],
'category' : ['asdf','asfa','asdfas','as'],
'num1' : [1, 1, 0, 0] ,
'target' : [1,0,0,1]})
df
dtarget=df['target']
dfeatures=df.drop('target', axis=1)
num = dfeatures.select_dtypes(include=["int64"]).columns.tolist()
cat = dfeatures.select_dtypes(include=["object"]).columns.tolist()
transformer = ColumnTransformer(
transformers=[
("cat", OneHotEncoder(), cat),
]
)
clf= DecisionTreeClassifier(criterion="entropy", max_depth = 5)
pipe = Pipeline(steps=[
('onehotenc', transformer),
('decisiontree', clf)
])
#Fit the training data to the pipeline
pipe.fit(dfeatures, dtarget)
pipe.named_steps['onehotenc'].get_feature_names_out().tolist(),
dot_data= tree.export_graphviz(clf,
out_file=None,
feature_names = num + pipe.named_steps['onehotenc'].get_feature_names_out().tolist(),
class_names= ['1', '0'],
filled = True)
The numeric feature isn't in your transformer. Since you don't want to do any changes to it, try letting it pass through. You can explicitly define passthrough columns, or pass the remainder. remainder is fine if you know that's the only other column that could ever be sent to the model.
transformer = ColumnTransformer(
transformers=[
("cat", OneHotEncoder(), cat),
],remainder='passthrough'
)
With this you will see your features names include the num1 column
pipe.named_steps['onehotenc'].get_feature_names_out().tolist()
Output
['cat__brand_NaN',
'cat__brand_aaaa',
'cat__brand_asdfasdf',
'cat__brand_sadfds',
'cat__category_as',
'cat__category_asdf',
'cat__category_asdfas',
'cat__category_asfa',
'remainder__num1']

How to create custom Pipeline in Python?

How can I create a custom Pipeline in python? I tried with sklearn pipeline but seems it not running successfully. Mostly I need my pre-process as a customize pipeline with a logistics model.
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import LabelEncoder
from sklearn import metrics
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
import eli5
from eli5.sklearn import PermutationImportance
from sklearn.pipeline import Pipeline, make_pipeline, FeatureUnion
from sklearn.preprocessing import FunctionTransformer
from sklearn.compose import ColumnTransformer
path = 'C:/Users/Desktop/'
df = pd.read_excel (path + "df.xlsx", sheet_name='df')
# import the BaseEstimator
from sklearn.base import BaseEstimator
# define the class OutletTypeEncoder
# custom transformer must have methods fit and transform
class OutletTypeEncoder(BaseEstimator):
def __init__(self):
pass
def fit(self, documents, y=None):
return self
def transform(self, df):
# replace NaN
df[['pdf_tbl_pn_identifier', 'pdf_tbl_qty_identifier', 'pdf_header_present']] = df[['pdf_tbl_pn_identifier', 'pdf_tbl_qty_identifier', 'pdf_header_present']].fillna(value=-999)
df[['pdf_tbl_cnt']] = df[['pdf_tbl_cnt']].fillna(value=0)
# Replace gt 1 count as 0
df['pdf_tbl_cnt'] = np.where( ( df['pdf_tbl_cnt'] == '1'), 1, 0)
df['part_cnt'] = np.where( (df['part_cnt'] == '1'), 1, 0)
# create numeric and categorica coulmns
obj_df= df[['pdf_tbl_pn_identifier','pdf_tbl_qty_identifier','pdf_header_present',
'pdf_body_pn_identifier','pdf_body_qty_identifier','pdf_model_rel_returned','pdf_model_ent_returned']]
num_df= df[['pdf_tbl_cnt', 'pdf_model_avg_relationship_score','pdf_model_avg_entity_score','part_cnt','matching']]
# Labelencoding for categorica columns and then
obj_df=obj_df.apply(LabelEncoder().fit_transform)
df = pd.concat([obj_df, num_df], axis=1)
df.reset_index(inplace=True, drop=True)
df.pdf_tbl_pn_identifier = df.pdf_tbl_pn_identifier.astype(str)
df.pdf_tbl_qty_identifier = df.pdf_tbl_qty_identifier.astype(str)
df.pdf_body_pn_identifier = df.pdf_body_pn_identifier.astype(str)
df.pdf_body_qty_identifier = df.pdf_body_qty_identifier.astype(str)
df.pdf_model_rel_returned = df.pdf_model_rel_returned.astype(str)
df.pdf_model_ent_returned = df.pdf_model_ent_returned.astype(str)
df.pdf_header_present = df.pdf_header_present.astype(str)
df.matching = df.matching.astype(str)
#df['pdf_tbl_cnt'] = df['pdf_tbl_cnt'].apply(np.int64)
df.pdf_tbl_cnt = df.pdf_tbl_cnt.apply(np.int64)
return df
feature_cols = df.drop(['matching'], axis=1)
X = feature_cols # Features
y = df.matching # Target variable
# split into train test sets
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.25,random_state=0)
logreg = LogisticRegression()
model_pipeline = Pipeline(steps=[('preprocess', OutletTypeEncoder()),
('logreg', LogisticRegression())
])
# fit the pipeline with the training data
model_pipeline.fit(X_train,y_train)
I am getting error as below. Plz help me out
UnboundLocalError: local variable 'df' referenced before assignment

I can't 'passthrough' a step in sklearn pipeline

I wanted to test different scaler in my pipeline, so I created a class that can take as parameter the scaler I want (Standard, MinMax etc..)
It works fine. But i want to specifiy in my param_grid to test without scaler. And I added 'passthrough' in my pipeline estimators, but it doesn't work and i get the following error :
AttributeError: 'str' object has no attribute 'set_params'
I know it might have something to do with the construction of my class but i can't find how to fix it.
Here is the code you can run to test.
# import dependencies
from sklearn.tree import DecisionTreeClassifier
from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV
from sklearn.preprocessing import StandardScaler, MinMaxScaler, RobustScaler
from sklearn.datasets import load_breast_cancer
from sklearn.base import BaseEstimator, TransformerMixin
import pandas as pd
class ScalerSelector(BaseEstimator, TransformerMixin):
def __init__(self, scaler=StandardScaler()):
super().__init__()
self.scaler = scaler
def fit(self, X, y=None):
return self.scaler.fit(X)
def transform(self, X, y=None):
return self.scaler.transform(X)
data = load_breast_cancer()
features = data["data"]
target = data["target"]
data = pd.DataFrame(data['data'], columns=data['feature_names'])
col_names = data.columns.tolist()
# scaler and encoder options
my_scaler = ScalerSelector()
preprocessor = ColumnTransformer(transformers = [('numerical', my_scaler, col_names)
])
# combine the preprocessor with LogisticRegression() using Pipeline
full_pipeline = Pipeline(steps = [('preprocessor', preprocessor),
('log_reg', LogisticRegression())
])
# set params combination I want to try
scaler_options = {'preprocessor': ['passthrough'],
'preprocessor__numerical__scaler':[StandardScaler(), RobustScaler(), MinMaxScaler()]}
# : ['passthrough', ScalerSelector()]
# initialize GridSearchCV using full_pipeline as final estimator
grid_cv = GridSearchCV(full_pipeline, param_grid = scaler_options)
# fit the data
grid_cv.fit(data, target)
# best params :
grid_cv.best_params_

How to test preprocessing combinations in nested pipeline using GridSearchCV?

I've been working on this classification problem using sklearn's Pipeline to combine the preprocessing step (scaling) and the cross validation step (GridSearchCV) using Logistic Regression.
Here is the simplified code:
# import dependencies
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder, StandardScaler, MinMaxScaler, RobustScaler
# scaler and encoder options
scaler = StandardScaler() # there are 3 options that I want to try
encoder = OneHotEncoder() # only one option, no need to GridSearch it
# use ColumnTransformer to apply different preprocesses to numerical and categorical columns
preprocessor = ColumnTransformer(transformers = [('categorical', encoder, cat_columns),
('numerical', scaler, num_columns),
])
# combine the preprocessor with LogisticRegression() using Pipeline
full_pipeline = Pipeline(steps = [('preprocessor', preprocessor),
('log_reg', LogisticRegression())])
What I'm trying to do, is to try different scaling methods (e.g. standard scaling, robust scaling, etc.) and after trying all of those, pick the scaling method that yields the best metric (i.e. accuracy). However, I don't know how to do this using the GridSearchCV:
from sklearn.model_selection import GridSearchCV
# set params combination I want to try
scaler_options = {'numerical':[StandardScaler(), RobustScaler(), MinMaxScaler()]}
# initialize GridSearchCV using full_pipeline as final estimator
grid_cv = GridSearchCV(full_pipeline, param_grid = scaler_options, cv = 5)
# fit the data
grid_cv.fit(X_train, y_train)
I know that the code above won't work, particularly because of the scaler_options that I've set as param_grid. I realize that the scaler_options I set can't be processed by GridSearchCV. Why? Because it isn't a hyperparameter of the pipeline (unlike 'log_reg__C', a hyperparameter from LogisticRegression() than can be accessed by the GridSearchCV). But instead its a component of the ColumnTransformer which I have nested inside the full_pipeline.
So the main question is, how do I automate GridSearchCV to test all of my scaler options? Since the scaler is a component of a sub-pipeline (i.e. the previous ColumnTransformer).
As you suggested you could create a class that takes in its __init()__ parameters, the scaler you want to use.
Then you could specify in your grid search parameters the Scaler your class should use to initialize the class.
I wrote that i hope it helps :
class ScalerSelector(BaseEstimator, TransformerMixin):
def __init__(self, scaler=StandardScaler()):
super().__init__()
self.scaler = scaler
def fit(self, X, y=None):
return self.scaler.fit(X)
def transform(self, X, y=None):
return self.scaler.transform(X)
Here you can find a full example that you can run to test :
# import dependencies
from sklearn.tree import DecisionTreeClassifier
from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
from sklearn.model_selection import GridSearchCV
from sklearn.preprocessing import StandardScaler, MinMaxScaler, RobustScaler
from sklearn.datasets import load_breast_cancer
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.preprocessing import StandardScaler, MinMaxScaler, RobustScaler
import pandas as pd
class ScalerSelector(BaseEstimator, TransformerMixin):
def __init__(self, scaler=StandardScaler()):
super().__init__()
self.scaler = scaler
def fit(self, X, y=None):
return self.scaler.fit(X)
def transform(self, X, y=None):
return self.scaler.transform(X)
data = load_breast_cancer()
features = data["data"]
target = data["target"]
data = pd.DataFrame(data['data'], columns=data['feature_names'])
col_names = data.columns.tolist()
# scaler and encoder options
my_scaler = ScalerSelector()
preprocessor = ColumnTransformer(transformers = [('numerical', my_scaler, col_names)
])
# combine the preprocessor with LogisticRegression() using Pipeline
full_pipeline = Pipeline(steps = [('preprocessor', preprocessor),
('log_reg', LogisticRegression())
])
# set params combination I want to try
scaler_options = {'preprocessor__numerical__scaler':[StandardScaler(), RobustScaler(), MinMaxScaler()]}
# initialize GridSearchCV using full_pipeline as final estimator
grid_cv = GridSearchCV(full_pipeline, param_grid = scaler_options)
# fit the data
grid_cv.fit(data, target)
# best params :
grid_cv.best_params_
You can fulfill what you intend without creating a custom transformer. And you can even pass the 'passthrough' argument into param_grid to experiment with the scenario where you don't want to do any scaling in that step at all.
In this example, suppose we want to investigate whether it is better for the model to impose a Scaler transformer on numerical features, num_features.
cat_features = selector(dtype_exclude='number')(train.drop('target', axis=1))
num_features = selector(dtype_include='number')(train.drop('target', axis=1))
cat_preprocessor = Pipeline(steps=[
('oh', OneHotEncoder(handle_unknown='ignore')),
('ss', StandardScaler())
])
num_preprocessor = Pipeline(steps=[
('pt', PowerTransformer(method='yeo-johnson')),
('ss', StandardScaler()) # Create a place holder for your test here !!!
])
preprocessor = ColumnTransformer(transformers=[
('cat', cat_preprocessor, cat_features),
('num', num_preprocessor, num_features)
])
model = Pipeline(steps=[
('prep', preprocessor),
('clf', RidgeClassifier())
])
X = train.drop('target', axis=1)
y = train['target']
param_grid = {
'prep__cat__ss': ['passthrough', StandardScaler(with_mean=False)] # 'passthrough',
}
gs = GridSearchCV(
estimator=model,
param_grid=param_grid,
scoring='roc_auc',
n_jobs=-1,
cv=2
)
gs.fit(X, y)

Categories

Resources