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
