ML_AI_training/MultClassPipe3.py
2022-03-16 10:11:13 +00:00

163 lines
5.6 KiB
Python

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Fri Mar 4 15:25:33 2022
@author: tanu
"""
#%%
import os, sys
import pandas as pd
import numpy as np
import pprint as pp
#from copy import deepcopy
from sklearn import linear_model
from sklearn.linear_model import LogisticRegression, LinearRegression
from sklearn.naive_bayes import BernoulliNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier
from sklearn.neural_network import MLPClassifier
from xgboost import XGBClassifier
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.compose import make_column_transformer
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score
from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef
from sklearn.metrics import make_scorer
from sklearn.metrics import classification_report
from sklearn.metrics import average_precision_score
from sklearn.model_selection import cross_validate
from sklearn.model_selection import train_test_split
from sklearn.model_selection import StratifiedKFold
from sklearn.pipeline import Pipeline
from sklearn.pipeline import make_pipeline
from sklearn.feature_selection import RFE
from sklearn.feature_selection import RFECV
import itertools
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
print(np.__version__)
print(pd.__version__)
from statistics import mean, stdev, median, mode
from imblearn.over_sampling import RandomOverSampler
from imblearn.over_sampling import SMOTE
from imblearn.pipeline import Pipeline
#from sklearn.datasets import make_classification
from sklearn.model_selection import cross_validate
from sklearn.model_selection import RepeatedStratifiedKFold
from sklearn.ensemble import AdaBoostClassifier
from imblearn.combine import SMOTEENN
from imblearn.under_sampling import EditedNearestNeighbours
#%%
rs = {'random_state': 42}
# Done: add preprocessing step with one hot encoder
# Done: get accuracy and other scores through K-fold stratified cv
scoring_fn = ({ 'fscore' : make_scorer(f1_score)
, 'mcc' : make_scorer(matthews_corrcoef)
, 'precision' : make_scorer(precision_score)
, 'recall' : make_scorer(recall_score)
, 'accuracy' : make_scorer(accuracy_score)
, 'roc_auc' : make_scorer(roc_auc_score)
#, 'jaccard' : make_scorer(jaccard_score)
})
# Multiple Classification - Model Pipeline
def MultClassPipelineCV(X_train, X_test, y_train, y_test, input_df, var_type = ['numerical', 'categorical','mixed']):
# determine categorical and numerical features
numerical_ix = input_df.select_dtypes(include=['int64', 'float64']).columns
numerical_ix
categorical_ix = input_df.select_dtypes(include=['object', 'bool']).columns
categorical_ix
# Determine preprocessing steps ~ var_type
if var_type == 'numerical':
t = [('num', MinMaxScaler(), numerical_ix)]
if var_type == 'categorical':
t = [('cat', OneHotEncoder(), categorical_ix)]
if var_type == 'mixed':
t = [('cat', OneHotEncoder(), categorical_ix)
, ('num', MinMaxScaler(), numerical_ix)]
col_transform = ColumnTransformer(transformers = t
, remainder='passthrough')
#%%
log_reg = LogisticRegression(**rs)
nb = BernoulliNB()
knn = KNeighborsClassifier()
svm = SVC(**rs)
mlp = MLPClassifier(max_iter=500, **rs)
dt = DecisionTreeClassifier(**rs)
et = ExtraTreesClassifier(**rs)
rf = RandomForestClassifier(**rs)
rf2 = RandomForestClassifier(
min_samples_leaf=50,
n_estimators=150,
bootstrap=True,
oob_score=True,
n_jobs=-1,
random_state=42,
max_features='auto')
xgb = XGBClassifier(**rs, verbosity=0)
models = [
('Logistic Regression', log_reg),
('Naive Bayes', nb),
('K-Nearest Neighbors', knn),
('SVM', svm),
('MLP', mlp),
('Decision Tree', dt),
('Extra Trees', et),
('Random Forest', rf),
('Random Forest2', rf2),
#('XGBoost', xgb)
]
skf_cv_scores = {}
for model_name, model_fn in models:
print('\nModel_name:', model_name
, '\nModel func:' , model_fn
, '\nList of models:', models)
# model_pipeline = Pipeline([
# ('pre' , MinMaxScaler())
# , ('model' , model_fn)])
model_pipeline = Pipeline([
('prep' , col_transform)
, ('model' , model_fn)])
print('Running model pipeline:', model_pipeline)
skf_cv = cross_validate(model_pipeline
, X_train
, y_train
, cv = 10
, scoring = scoring_fn
, return_train_score = True)
skf_cv_scores[model_name] = {}
for key, value in skf_cv.items():
print('\nkey:', key, '\nvalue:', value)
print('\nmean value:', mean(value))
skf_cv_scores[model_name][key] = round(mean(value),2)
#pp.pprint(skf_cv_scores)
return(skf_cv_scores)