saving work
This commit is contained in:
parent
a1631ea54b
commit
e28a296d98
8 changed files with 153 additions and 212 deletions
|
|
@ -6,51 +6,79 @@ Created on Fri Mar 4 15:25:33 2022
|
|||
@author: tanu
|
||||
"""
|
||||
#%%
|
||||
|
||||
import os, sys
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
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 sklearn.pipeline import Pipeline
|
||||
from xgboost import XGBClassifier
|
||||
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
|
||||
|
||||
from sklearn.compose import ColumnTransformer
|
||||
from sklearn.preprocessing import StandardScaler
|
||||
from sklearn.preprocessing import MinMaxScaler, OneHotEncoder
|
||||
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.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.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
|
||||
# TODO: supply stratified K-fold cv train and test data
|
||||
# TODO: get accuracy and other scores through K-fold cv
|
||||
# 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 MultClassPipeSKF(input_df, y_targetF, var_type = ['numerical', 'categorical','mixed'], skf_splits = 10):
|
||||
def MultClassPipelineCV(X_train, X_test, y_train, y_test, input_df, var_type = ['numerical', 'categorical','mixed']):
|
||||
|
||||
'''
|
||||
@ param input_df: input features
|
||||
@ type: df (gets converted to np.array for stratified Kfold, and helps identify names to apply column transformation)
|
||||
|
||||
@param y_outputF: target (or output) feature
|
||||
@type: df or np.array
|
||||
|
||||
|
||||
returns
|
||||
multiple classification model scores
|
||||
|
||||
'''
|
||||
# Determine categorical and numerical features
|
||||
# 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
|
||||
|
|
@ -69,129 +97,67 @@ def MultClassPipeSKF(input_df, y_targetF, var_type = ['numerical', 'categorical'
|
|||
|
||||
col_transform = ColumnTransformer(transformers = t
|
||||
, remainder='passthrough')
|
||||
|
||||
#%% Define classification models to run
|
||||
|
||||
#%%
|
||||
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')
|
||||
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)
|
||||
xgb = XGBClassifier(**rs, verbosity=0)
|
||||
|
||||
clfs = [
|
||||
('Logistic Regression' , log_reg)
|
||||
#, ('Naive Bayes' , nb)
|
||||
, ('K-Nearest Neighbors', knn)
|
||||
, ('SVM' , svm)
|
||||
, ('MLP' , mlp)
|
||||
, ('Decision Tree' , dt)
|
||||
, ('Extra Trees' , et)
|
||||
, ('Random Forest' , rf)
|
||||
, ('Naive Bayes' , nb)
|
||||
|
||||
#, ('Random Forest2' , rf2)
|
||||
#, ('XGBoost' , xgb)
|
||||
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 = StratifiedKFold(n_splits = skf_splits
|
||||
, shuffle = True
|
||||
#, random_state = seed_skf
|
||||
, **rs)
|
||||
|
||||
X_array = np.array(input_df)
|
||||
Y = y_targetF
|
||||
|
||||
# Initialise score metrics list to store skf results
|
||||
# fscoreL = []
|
||||
# mccL = []
|
||||
# presL = []
|
||||
# recallL = []
|
||||
# accuL = []
|
||||
# roc_aucL = []
|
||||
skf_dict = {}
|
||||
|
||||
skf_cv_scores = {}
|
||||
|
||||
for model_name, model_fn in models:
|
||||
print('\nModel_name:', model_name
|
||||
, '\nModel func:' , model_fn
|
||||
, '\nList of models:', models)
|
||||
|
||||
#scores_df = pd.DataFrame()
|
||||
for train_index, test_index in skf.split(input_df, y_targetF):
|
||||
x_train_fold, x_test_fold = input_df.iloc[train_index], input_df.iloc[test_index]
|
||||
y_train_fold, y_test_fold = y_targetF.iloc[train_index], y_targetF.iloc[test_index]
|
||||
#fscoreL = {}
|
||||
# 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)
|
||||
|
||||
# for train_index, test_index in skf.split(X_array, Y):
|
||||
# print('\nSKF train index:', train_index
|
||||
# , '\nSKF test index:', test_index)
|
||||
# x_train_fold, x_test_fold = X_array[train_index], X_array[test_index]
|
||||
# y_train_fold, y_test_fold = Y[train_index], Y[test_index]
|
||||
|
||||
clf_scores_df = pd.DataFrame()
|
||||
|
||||
for clf_name, clf in clfs:
|
||||
print('\nRunning the following classification models'
|
||||
, clf_name)
|
||||
|
||||
model_pipeline = Pipeline(steps=[('prep' , col_transform)
|
||||
, ('classifier' , clf)])
|
||||
|
||||
# model_pipeline = Pipeline(steps=[('prep' , MinMaxScaler())
|
||||
# , ('classifier' , clf)])
|
||||
|
||||
|
||||
model_pipeline.fit(x_train_fold, y_train_fold)
|
||||
y_pred_fold = model_pipeline.predict(x_test_fold)
|
||||
|
||||
#----------------
|
||||
# Model metrics
|
||||
#----------------
|
||||
# F1-Score
|
||||
fscore = f1_score(y_test_fold, y_pred_fold)
|
||||
fscoreL[clf_name].append(fscore)
|
||||
print('fscoreL Len: ', len(fscoreL))
|
||||
#fscoreM = mean(fscoreL[clf])
|
||||
|
||||
# Matthews correlation coefficient
|
||||
mcc = matthews_corrcoef(y_test_fold, y_pred_fold)
|
||||
mccL[clf_name].append(mcc)
|
||||
mccM = mean(mccL)
|
||||
|
||||
# # Precision
|
||||
# pres = precision_score(y_test_fold, y_pred_fold)
|
||||
# presL.append(pres)
|
||||
# presM = mean(presL)
|
||||
|
||||
# # Recall
|
||||
# recall = recall_score(y_test_fold, y_pred_fold)
|
||||
# recallL.append(recall)
|
||||
# recallM = mean(recallL)
|
||||
|
||||
# # Accuracy
|
||||
# accu = accuracy_score(y_test_fold, y_pred_fold)
|
||||
# accuL.append(accu)
|
||||
# accuM = mean(accuL)
|
||||
|
||||
# # ROC_AUC
|
||||
# roc_auc = roc_auc_score(y_test_fold, y_pred_fold)
|
||||
# roc_aucL.append(roc_auc)
|
||||
# roc_aucM = mean(roc_aucL)
|
||||
|
||||
clf_scores_df = clf_scores_df.append({'Model' : clf_name
|
||||
,'F1_score' : fscoreM
|
||||
, 'MCC' : mccM
|
||||
, 'Precision': presM
|
||||
, 'Recall' : recallM
|
||||
, 'Accuracy' : accuM
|
||||
, 'ROC_curve': roc_aucM}
|
||||
, ignore_index = True)
|
||||
return(clf_scores_df)
|
||||
#scores_df = scores_df.append(clf_scores_df)
|
||||
# return clf_scores_df
|
||||
Loading…
Add table
Add a link
Reference in a new issue