ML_AI_training/my_data10.py

272 lines
No EOL
8.8 KiB
Python

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Sat Mar 5 12:57:32 2022
@author: tanu
"""
#%%
# Data, etc for now comes from my_data6.py and/or my_data5.py
#%% Specify dir and import functions
homedir = os.path.expanduser("~")
os.chdir(homedir + "/git/ML_AI_training/")
#%% Try combinations
#import sys, os
#os.system("imports.py")
def precision(y_true,y_pred):
return precision_score(y_true,y_pred,pos_label = 1)
def recall(y_true,y_pred):
return recall_score(y_true, y_pred, pos_label = 1)
def f1(y_true,y_pred):
return f1_score(y_true, y_pred, pos_label = 1)
#%% Check df features
numerical_features_df.shape
categorical_features_df.shape
all_features_df.shape
all_features_df.dtypes
#%% Simple train and test data splits
target = target1
#target = target3
X_trainN, X_testN, y_trainN, y_testN = train_test_split(numerical_features_df,
target,
test_size = 0.33,
random_state = 42)
X_trainC, X_testC, y_trainC, y_testC = train_test_split(categorical_features_df,
target,
test_size = 0.33,
random_state = 42)
X_train, X_test, y_train, y_test = train_test_split(all_features_df,
target,
test_size = 0.33,
random_state = 42)
#%% Stratified K-fold: Single model
model1 = Pipeline(steps = [('preprocess', MinMaxScaler())
, ('log_reg', LogisticRegression(class_weight = 'balanced')) ])
model1
rs = {'random_state': 42}
log_reg = LogisticRegression(**rs)
nb = BernoulliNB()
clfs = [('Logistic Regression', log_reg)
,('Naive Bayes', nb)]
seed_skf = 42
skf = StratifiedKFold(n_splits = 10
, shuffle = True
, random_state = seed_skf)
X_array = np.array(numerical_features_df)
Y = target1
model_scores_df = pd.DataFrame()
fscoreL = []
mccL = []
presL = []
recallL = []
accuL = []
roc_aucL = []
for train_index, test_index in skf.split(X_array, Y):
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]
model1.fit(x_train_fold, y_train_fold)
y_pred_fold = model1.predict(x_test_fold)
#----------------
# Model metrics
#----------------
# F1-Score
fscore = f1_score(y_test_fold, y_pred_fold)
fscoreL.append(fscore)
fscoreM = mean(fscoreL)
# Matthews correlation coefficient
mcc = matthews_corrcoef(y_test_fold, y_pred_fold)
mccL.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)
model_scores_df = model_scores_df.append({'Model' : model1.steps[1][0]
,'F1_score' : fscoreM
, 'MCC' : mccM
, 'Precision': presM
, 'Recall' : recallM
, 'Accuracy' : accuM
, 'ROC_curve': roc_aucM}
, ignore_index = True)
print('\nModel metrics:', model_scores_df)
#%% stratified KFold: Multiple_models:
input_df = numerical_features_df
#X_array = np.array(input_df)
Y = target1
var_type = 'numerical'
input_df = all_features_df
#X_array = np.array(input_df)
Y = target1
var_type = 'mixed'
input_df = categorical_features_df
#X_array = np.array(input_df)
Y = target1
var_type = 'categorical'
#=================
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')
rs = {'random_state': 42}
#log_reg = LogisticRegression(**rs)
log_reg = LogisticRegression(class_weight = 'balanced')
nb = BernoulliNB()
rf = RandomForestClassifier(**rs)
clfs = [('Logistic Regression', log_reg)
,('Naive Bayes', nb)
, ('Random Forest' , rf)
]
#seed_skf = 42
skf = StratifiedKFold(n_splits = 10
, shuffle = True
#, random_state = seed_skf
, **rs)
#scores_df = pd.DataFrame()
fscoreL = []
mccL = []
presL = []
recallL = []
accuL = []
roc_aucL = []
for train_index, test_index in skf.split(input_df, Y):
print('\nSKF train index:', train_index
, '\nSKF test index:', test_index)
x_train_fold, x_test_fold = input_df.iloc[train_index], input_df.iloc[test_index]
y_train_fold, y_test_fold = Y.iloc[train_index], Y.iloc[test_index]
# 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:
# model2 = Pipeline(steps=[('preprocess', MinMaxScaler())
# , ('classifier', clf)])
model2 = Pipeline(steps=[('preprocess', col_transform)
, ('classifier', clf)])
model2.fit(x_train_fold, y_train_fold)
y_pred_fold = model2.predict(x_test_fold)
#----------------
# Model metrics
#----------------
# F1-Score
fscore = f1_score(y_test_fold, y_pred_fold)
fscoreL.append(fscore)
fscoreM = mean(fscoreL)
# Matthews correlation coefficient
mcc = matthews_corrcoef(y_test_fold, y_pred_fold)
mccL.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)
#scores_df = scores_df.append(clf_scores_df)
#%% Call functions
tN_res = MultClassPipeline(X_trainN, X_testN, y_trainN, y_testN)
tN_res
t2_res = MultClassPipeline2(X_train, X_test, y_train, y_test, input_df = all_features_df)
t2_res
#CHECK: numbers are awfully close to each other!
t3_res = MultClassPipeSKF(input_df = numerical_features_df
, y_targetF = target1
, var_type = 'numerical'
, skf_splits = 10)
t3_res
#CHECK: numbers are awfully close to each other!
t4_res = MultClassPipeSKF(input_df = all_features_df
, y_targetF = target1
, var_type = 'mixed'
, skf_splits = 10)
t4_res