tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

moved logo_skf function to del as using the MultClfs for combined data

Browse source
This commit is contained in:
Tanushree Tunstall 2022-07-28 12:24:24 +01:00
parent a6532ddfa3
commit 2c50124b1b
8 changed files with 71 additions and 1735 deletions
Download patch file Download diff file Expand all files Collapse all files

136
scripts/ml/combined_model/cm_datai.py
View file

@ -1,136 +0,0 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Jun 29 19:44:06 2022
@author: tanu
"""
import sys, os
import pandas as pd
import numpy as np
import re
from copy import deepcopy
from sklearn import linear_model
from sklearn import datasets
from collections import Counter
###############################################################################
homedir = os.path.expanduser("~")
sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml/ml_functions')
sys.path
###############################################################################
outdir = homedir + '/git/LSHTM_ML/output/combined/'
#====================
# Import ML functions
#====================
from ml_data_combined import *
from MultClfs_logo_skf import *
#from GetMLData import *
#from SplitTTS import *
skf_cv = StratifiedKFold(n_splits = 10 , shuffle = True, random_state = 42)
#logo = LeaveOneGroupOut()
########################################################################
# COMPLETE data: No tts_split
########################################################################
#%%
def CMLogoData(cm_input_df = pd.DataFrame()
, all_genes = ["embb", "katg", "rpob", "pnca", "gid", "alr"]
, bts_genes = ["embb", "katg"
, "rpob", "pnca", "gid"
]
, cols_to_drop = ['dst', 'dst_mode', 'gene_name']
, target_var = 'dst_mode'
, gene_group = 'gene_name'
, std_gene_omit = []
):
cm_dataD = {}
for bts_gene in bts_genes:
print('\n BTS gene:', bts_gene)
if not std_gene_omit:
training_genesL = ['alr']
else:
training_genesL = []
tr_gene_omit = std_gene_omit + [bts_gene]
n_tr_genes = (len(bts_genes) - (len(std_gene_omit)))
#n_total_genes = (len(bts_genes) - len(std_gene_omit))
n_total_genes = len(all_genes)
training_genesL = training_genesL + list(set(bts_genes) - set(tr_gene_omit))
#training_genesL = [element for element in bts_genes if element not in tr_gene_omit]
print('\nTotal genes: ', n_total_genes
,'\nTraining on:', n_tr_genes
,'\nTraining on genes:', training_genesL
, '\nOmitted genes:', tr_gene_omit
, '\nBlind test gene:', bts_gene)
tts_split_type = "logo_skf_BT_" + bts_gene
outFile = outdir + str(n_tr_genes+1) + "genes_" + tts_split_type + ".csv"
print(outFile)
bts_geneD = {}
#-------
# training
#------
cm_training_df = cm_input_df[~cm_input_df['gene_name'].isin(tr_gene_omit)]
cm_X = cm_training_df.drop(cols_to_drop, axis=1, inplace=False)
#cm_y = cm_training_df.loc[:,'dst_mode']
cm_y = cm_training_df.loc[:, target_var]
gene_group = cm_training_df.loc[:,'gene_name']
print('\nTraining data dim:', cm_X.shape
, '\nTraining Target dim:', cm_y.shape)
if all(cm_X.columns.isin(cols_to_drop) == False):
print('\nChecked training df does NOT have Target var')
else:
sys.exit('\nFAIL: training data contains Target var')
#---------------
# BTS: genes
#---------------
cm_test_df = cm_input_df[cm_input_df['gene_name'].isin([bts_gene])]
cm_bts_X = cm_test_df.drop(cols_to_drop, axis = 1, inplace = False)
#cm_bts_y = cm_test_df.loc[:, 'dst_mode']
cm_bts_y = cm_test_df.loc[:, target_var]
print('\nTEST data dim:', cm_bts_X.shape
, '\nTEST Target dim:', cm_bts_y.shape)
bts_geneD = {'cm_X' : cm_X
, 'cm_y' : cm_y
, 'cm_bts_X': cm_bts_X
, 'cm_bts_y': cm_bts_y}
cm_dataD[bts_gene] = bts_geneD
return(cm_dataD)
#%%
df_complete_6g = CMLogoData(cm_input_df = combined_df, std_gene_omit=[] )
df_complete_5g = CMLogoData(cm_input_df = combined_df, std_gene_omit=['alr'])
# checks
len(df_complete_6g['embb']['cm_X'])
#len(df_complete_6g['embb']['cm_y'])
len(df_complete_5g['embb']['cm_X'])
#len(df_complete_5g['embb']['cm_y'])
df_actual_6g = CMLogoData(cm_input_df = combined_df_actual, std_gene_omit=[] )
df_actual_5g = CMLogoData(cm_input_df = combined_df_actual, std_gene_omit=['alr'])
len(df_actual_6g['embb']['cm_X'])
len(df_actual_5g['embb']['cm_X'])

3
scripts/ml/combined_model/cm_logo_skf.py
View file

@ -176,7 +176,8 @@ def CMLogoSkf(cm_input_df
print("Running Multiple models on LOGO with SKF") print("Running Multiple models on LOGO with SKF")
#%%:Running Multiple models on LOGO with SKF #%%:Running Multiple models on LOGO with SKF
cD3_v2 = MultModelsCl_logo_skf(input_df = cm_X # cD3_v2 = MultModelsCl_logo_skf(input_df = cm_X # two func were identical excpet for name
cD3_v2 = MultModelsCl(input_df = cm_X
, target = cm_y , target = cm_y
, sel_cv = skf_cv , sel_cv = skf_cv
, tts_split_type = tts_split_type , tts_split_type = tts_split_type

153
scripts/ml/ml_functions/CHECK_model.py
View file

@ -1,153 +0,0 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Thu Jul 7 22:18:14 2022
@author: tanu
"""
# Create a pipeline that standardizes the data then creates a model
import pandas as pd
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
# load data
url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv"
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv(url, names=names)
array = dataframe.values
X = array[:,0:8]
X = pd.DataFrame(X)
Y = array[:,8]
Y = pd.DataFrame(Y)
kfold = KFold(n_splits=1, random_state=None)
spl_type = "check"
fooD1 = MultModelsCl(input_df = X
, target = Y
, sel_cv = kfold
, run_blind_test = False
#, blind_test_df = df2['X_bts']
#, blind_test_target = df2['y_bts']
, add_cm = False
, add_yn = False
, tts_split_type = spl_type
, resampling_type = 'none' # default
, var_type = ['mixed']
, scale_numeric = ['std']
, return_formatted_output = True
)
# create pipeline
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('lda', LinearDiscriminantAnalysis()))
model = Pipeline(estimators)
# evaluate pipeline
seed = 7
#kfold = KFold(n_splits=10, random_state=seed)
kfold = KFold(n_splits=10, random_state=None)
results = cross_val_score(model, X, Y, cv=kfold)
print(results.mean())
results_A = round(results.mean(),2)
results2 = cross_val_score(model, X, Y, cv=kfold, scoring = "recall")
print(results2.mean())
results_R = round(results2.mean(),2)
results3 = cross_val_score(model, X, Y, cv=kfold, scoring = "precision")
print(results3.mean())
results_P = round(results3.mean(),2)
results4 = cross_val_score(model, X, Y, cv=kfold, scoring = "f1")
print(results4.mean())
results_f1 = round(results4.mean(),2)
results5 = cross_val_score(model, X, Y, cv=kfold, scoring = "jaccard")
print(results5.mean())
results_J = round(results5.mean(),2)
results6 = cross_val_score(model, X, Y, cv=kfold, scoring = "matthews_corrcoef")
print(results6.mean())
results_mcc = round(results6.mean(),2)
#%%
import numpy as np
from sklearn.compose import ColumnTransformer
from sklearn.datasets import fetch_openml
from sklearn.pipeline import Pipeline, make_pipeline
from sklearn.decomposition import PCA
from sklearn.impute import SimpleImputer, KNNImputer
from sklearn.preprocessing import RobustScaler, OneHotEncoder
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split, cross_val_score, RandomizedSearchCV
X_train, X_test, y_train, y_test = train_test_split(X, Y, stratify=Y, test_size=0.2)
fooD2 = MultModelsCl(input_df = X_train
, target = y_train
, sel_cv = kfold
, run_blind_test = True
, blind_test_df = X_test
, blind_test_target = y_test
, add_cm = False
, add_yn = False
, tts_split_type = spl_type
, resampling_type = 'none' # default
, var_type = ['mixed']
, scale_numeric = ['std']
, return_formatted_output = True
)
# fitting and predicting on test
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
results_A = round(cross_val_score(model, X_train, y_train, cv=kfold).mean(),2)
print(results_A)
results_P = round(cross_val_score(model, X_train, y_train, cv=kfold, scoring = "precision").mean(),2)
print(results_P)
results_R = round(cross_val_score(model, X_train, y_train, cv=kfold, scoring = "recall").mean(),2)
print(results_R)
results_F = round(cross_val_score(model, X_train, y_train, cv=kfold, scoring = "f1").mean(),2)
print(results_F)
results_J = round(cross_val_score(model, X_train, y_train, cv=kfold, scoring = "jaccard").mean(),2)
print(results_J)
results_M = round(cross_val_score(model, X_train, y_train, cv=kfold, scoring = "matthews_corrcoef").mean(),2)
print(results_M)
print('\nCV example accuracy:', results_P)
print('BTS example accuracy:', round(precision_score(y_test, y_pred),2))
print('\nCV example accuracy:', results_J)
print('BTS example accuracy:', round(jaccard_score(y_test, y_pred),2))
print('\nCV example accuracy:', results_R)
print('BTS example accuracy:', round(recall_score(y_test, y_pred),2))
print('\nCV example accuracy:', results_F)
print('BTS example accuracy:', round(f1_score(y_test, y_pred),2))
print('\nCV example accuracy:', results_A)
print('BTS example accuracy:', round(accuracy_score(y_test, y_pred),2))
print('\nCV example accuracy:', results_M)
print('BTS example accuracy:', round(matthews_corrcoef(y_test, y_pred),2))

14
scripts/ml/ml_functions/MultClfs.py
View file

@ -92,10 +92,10 @@ scoring_fn = ({ 'mcc' : make_scorer(matthews_corrcoef)
, 'roc_auc' : make_scorer(roc_auc_score) , 'roc_auc' : make_scorer(roc_auc_score)
, 'jcc' : make_scorer(jaccard_score) , 'jcc' : make_scorer(jaccard_score)
}) })
# for sel_cv INSIDE FUNCTION CALL NOW
#skf_cv = StratifiedKFold(n_splits = 10 #skf_cv = StratifiedKFold(n_splits = 10
# #, shuffle = False, random_state= None) # #, shuffle = False, random_state= None)
# , shuffle = True,**rs) # , shuffle = True, **rs)
#rskf_cv = RepeatedStratifiedKFold(n_splits = 10 #rskf_cv = RepeatedStratifiedKFold(n_splits = 10
# , n_repeats = 3 # , n_repeats = 3
@ -149,7 +149,8 @@ scoreBT_mapD = {'bts_mcc' : 'MCC'
# Run Multiple Classifiers # Run Multiple Classifiers
############################ ############################
# Multiple Classification - Model Pipeline # Multiple Classification - Model Pipeline
def MultModelsCl(input_df, target def MultModelsCl(input_df
, target
, sel_cv , sel_cv
, tts_split_type , tts_split_type
, resampling_type , resampling_type
@ -357,10 +358,9 @@ def MultModelsCl(input_df, target
y_pred = cross_val_predict(model_pipeline y_pred = cross_val_predict(model_pipeline
, input_df , input_df
, target , target
#, commented out thing, , cv = sel_cv
, cv=sel_cv #, groups = group
, **njobs , **njobs)
)
#_tn, _fp, _fn, _tp = confusion_matrix(y_pred, y).ravel() # internally #_tn, _fp, _fn, _tp = confusion_matrix(y_pred, y).ravel() # internally
tn, fp, fn, tp = confusion_matrix(y_pred, target).ravel() tn, fp, fn, tp = confusion_matrix(y_pred, target).ravel()

553
scripts/ml/ml_functions/MultClfs_SIMPLE.py
View file

@ -1,553 +0,0 @@
#!/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 import datasets
from collections import Counter
from sklearn.linear_model import LogisticRegression, LogisticRegressionCV
from sklearn.linear_model import RidgeClassifier, RidgeClassifierCV, SGDClassifier, PassiveAggressiveClassifier
from sklearn.naive_bayes import BernoulliNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier, ExtraTreeClassifier
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier, AdaBoostClassifier, GradientBoostingClassifier, BaggingClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.gaussian_process import GaussianProcessClassifier, kernels
from sklearn.gaussian_process.kernels import RBF, DotProduct, Matern, RationalQuadratic, WhiteKernel
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis, QuadraticDiscriminantAnalysis
from sklearn.neural_network import MLPClassifier
from sklearn.svm import SVC
from xgboost import XGBClassifier
from sklearn.naive_bayes import MultinomialNB
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.compose import make_column_transformer
from sklearn.metrics import make_scorer, confusion_matrix, accuracy_score, balanced_accuracy_score, precision_score, average_precision_score, recall_score
from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef, jaccard_score, classification_report
# added
from sklearn.model_selection import train_test_split, cross_validate, cross_val_score, LeaveOneOut, KFold, RepeatedKFold, cross_val_predict
from sklearn.model_selection import train_test_split, cross_validate, cross_val_score
from sklearn.model_selection import StratifiedKFold,RepeatedStratifiedKFold, RepeatedKFold
from sklearn.pipeline import Pipeline, make_pipeline
from sklearn.feature_selection import RFE, RFECV
import itertools
import seaborn as sns
import matplotlib.pyplot as plt
from statistics import mean, stdev, median, mode
from imblearn.over_sampling import RandomOverSampler
from imblearn.under_sampling import RandomUnderSampler
from imblearn.over_sampling import SMOTE
from sklearn.datasets import make_classification
from imblearn.combine import SMOTEENN
from imblearn.combine import SMOTETomek
from imblearn.over_sampling import SMOTENC
from imblearn.under_sampling import EditedNearestNeighbours
from imblearn.under_sampling import RepeatedEditedNearestNeighbours
from sklearn.model_selection import GridSearchCV
from sklearn.base import BaseEstimator
from sklearn.impute import KNNImputer as KNN
import json
import argparse
import re
from sklearn.decomposition import PCA
#%% GLOBALS
rs = {'random_state': 42}
njobs = {'n_jobs': os.cpu_count() } # the number of jobs should equal the number of CPU cores
scoring_fn = ({ 'mcc' : make_scorer(matthews_corrcoef)
, 'fscore' : make_scorer(f1_score)
, 'precision' : make_scorer(precision_score)
, 'recall' : make_scorer(recall_score)
, 'accuracy' : make_scorer(accuracy_score)
, 'roc_auc' : make_scorer(roc_auc_score)
, 'jcc' : make_scorer(jaccard_score)
})
skf_cv = StratifiedKFold(n_splits = 10
#, shuffle = False, random_state= None)
, shuffle = True,**rs)
rskf_cv = RepeatedStratifiedKFold(n_splits = 10
, n_repeats = 3
, **rs)
mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
###############################################################################
score_type_ordermapD = { 'mcc' : 1
, 'fscore' : 2
, 'jcc' : 3
, 'precision' : 4
, 'recall' : 5
, 'accuracy' : 6
, 'roc_auc' : 7
, 'TN' : 8
, 'FP' : 9
, 'FN' : 10
, 'TP' : 11
, 'trainingY_neg': 12
, 'trainingY_pos': 13
, 'blindY_neg' : 14
, 'blindY_pos' : 15
, 'fit_time' : 16
, 'score_time' : 17
}
scoreCV_mapD = {'test_mcc' : 'MCC'
, 'test_fscore' : 'F1'
, 'test_precision' : 'Precision'
, 'test_recall' : 'Recall'
, 'test_accuracy' : 'Accuracy'
, 'test_roc_auc' : 'ROC_AUC'
, 'test_jcc' : 'JCC'
}
scoreBT_mapD = {'bts_mcc' : 'MCC'
, 'bts_fscore' : 'F1'
, 'bts_precision' : 'Precision'
, 'bts_recall' : 'Recall'
, 'bts_accuracy' : 'Accuracy'
, 'bts_roc_auc' : 'ROC_AUC'
, 'bts_jcc' : 'JCC'
}
#%%############################################################################
############################
# MultModelsCl()
# Run Multiple Classifiers
############################
# Multiple Classification - Model Pipeline
def MultModelsCl(input_df, target
, sel_cv
, blind_test_df
, blind_test_target
, tts_split_type
, resampling_type = 'none' # default
, add_cm = True # adds confusion matrix based on cross_val_predict
, add_yn = True # adds target var class numbers
, var_type = ['numerical', 'categorical','mixed']
, scale_numeric = ['min_max', 'std', 'min_max_neg', 'none']
, run_blind_test = True
, return_formatted_output = True):
'''
@ param input_df: input features
@ type: df with input features WITHOUT the target variable
@param target: target (or output) feature
@type: df or np.array or Series
@param skv_cv: stratifiedK fold int or object to allow shuffle and random state to pass
@type: int or StratifiedKfold()
@var_type: numerical, categorical and mixed to determine what col_transform to apply (MinMaxScalar and/or one-hot encoder)
@type: list
returns
Dict containing multiple classification scores for each model and mean of each Stratified Kfold including training
'''
#======================================================
# 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 = [('num', MinMaxScaler(), numerical_ix)
# # , ('cat', OneHotEncoder(), categorical_ix) ]
# if var_type == 'mixed':
# t = [('cat', OneHotEncoder(), categorical_ix) ]
if type(var_type) == list:
var_type = str(var_type[0])
else:
var_type = var_type
if var_type in ['numerical','mixed']:
if scale_numeric == ['none']:
t = [('cat', OneHotEncoder(), categorical_ix)]
if scale_numeric != ['none']:
if scale_numeric == ['min_max']:
scaler = MinMaxScaler()
if scale_numeric == ['min_max_neg']:
scaler = MinMaxScaler(feature_range=(-1, 1))
if scale_numeric == ['std']:
scaler = StandardScaler()
t = [('num', scaler, numerical_ix)
, ('cat', OneHotEncoder(), categorical_ix)]
if var_type == 'categorical':
t = [('cat', OneHotEncoder(), categorical_ix)]
col_transform = ColumnTransformer(transformers = t
, remainder='passthrough')
#======================================================
# Specify multiple Classification Models
#======================================================
models = [('AdaBoost Classifier' , AdaBoostClassifier(**rs) )
, ('Bagging Classifier' , BaggingClassifier(**rs, **njobs, bootstrap = True, oob_score = True, verbose = 3, n_estimators = 100) )
, ('Decision Tree' , DecisionTreeClassifier(**rs) )
, ('Extra Tree' , ExtraTreeClassifier(**rs) )
, ('Extra Trees' , ExtraTreesClassifier(**rs) )
, ('Gradient Boosting' , GradientBoostingClassifier(**rs) )
, ('Gaussian NB' , GaussianNB() )
, ('Gaussian Process' , GaussianProcessClassifier(**rs) )
, ('K-Nearest Neighbors' , KNeighborsClassifier() )
, ('LDA' , LinearDiscriminantAnalysis() )
, ('Logistic Regression' , LogisticRegression(**rs) )
, ('Logistic RegressionCV' , LogisticRegressionCV(cv = 3, **rs))
, ('MLP' , MLPClassifier(max_iter = 500, **rs) )
, ('Multinomial' , MultinomialNB() )
, ('Naive Bayes' , BernoulliNB() )
, ('Passive Aggresive' , PassiveAggressiveClassifier(**rs, **njobs) )
, ('QDA' , QuadraticDiscriminantAnalysis() )
# , ('Random Forest' , RandomForestClassifier(**rs, n_estimators = 1000, **njobs ) )
, ('Random Forest2' , RandomForestClassifier(min_samples_leaf = 5
, n_estimators = 1000
, bootstrap = True
, oob_score = True
, **njobs
, **rs
, max_features = 'auto') )
, ('Ridge Classifier' , RidgeClassifier(**rs) )
, ('Ridge ClassifierCV' , RidgeClassifierCV(cv = 3) )
, ('SVC' , SVC(**rs) )
, ('Stochastic GDescent' , SGDClassifier(**rs, **njobs) )
, ('XGBoost' , XGBClassifier(**rs, verbosity = 0, use_label_encoder =False, **njobs) )
]
mm_skf_scoresD = {}
print('\n==============================================================\n'
, '\nRunning several classification models (n):', len(models)
,'\nList of models:')
for m in models:
print(m)
print('\n================================================================\n')
index = 1
for model_name, model_fn in models:
print('\nRunning classifier:', index
, '\nModel_name:' , model_name
, '\nModel func:' , model_fn)
index = index+1
model_pipeline = Pipeline([
('prep' , col_transform)
, ('model' , model_fn)])
# model_pipeline = Pipeline([
# ('prep' , col_transform)
# , ('pca' , PCA(n_components = 2))
# , ('model' , model_fn)])
print('\nRunning model pipeline:', model_pipeline)
skf_cv_modD = cross_validate(model_pipeline
, input_df
, target
, cv = sel_cv
, scoring = scoring_fn
, return_train_score = True)
#==============================
# Extract mean values for CV
#==============================
mm_skf_scoresD[model_name] = {}
for key, value in skf_cv_modD.items():
print('\nkey:', key, '\nvalue:', value)
print('\nmean value:', np.mean(value))
mm_skf_scoresD[model_name][key] = round(np.mean(value),2)
# ADD more info: meta data related to input df
mm_skf_scoresD[model_name]['resampling'] = resampling_type
mm_skf_scoresD[model_name]['n_training_size'] = len(input_df)
mm_skf_scoresD[model_name]['n_trainingY_ratio'] = round(Counter(target)[0]/Counter(target)[1], 2)
mm_skf_scoresD[model_name]['n_features'] = len(input_df.columns)
mm_skf_scoresD[model_name]['tts_split'] = tts_split_type
#######################################################################
#======================================================
# Option: Add confusion matrix from cross_val_predict
# Understand and USE with caution
#======================================================
if add_cm:
cmD = {}
# Calculate cm
y_pred = cross_val_predict(model_pipeline, input_df, target, cv = sel_cv, **njobs)
#_tn, _fp, _fn, _tp = confusion_matrix(y_pred, y).ravel() # internally
tn, fp, fn, tp = confusion_matrix(y_pred, target).ravel()
# Build cm dict
cmD = {'TN' : tn
, 'FP': fp
, 'FN': fn
, 'TP': tp}
# Update cv dict cmD
mm_skf_scoresD[model_name].update(cmD)
#=============================================
# Option: Add targety numbers for data
#=============================================
if add_yn:
tnD = {}
# Build tn numbers dict
tnD = {'n_trainingY_neg' : Counter(target)[0]
, 'n_trainingY_pos' : Counter(target)[1] }
# Update cv dict with cmD and tnD
mm_skf_scoresD[model_name].update(tnD)
#%%
#=========================
# Option: Blind test (bts)
#=========================
if run_blind_test:
btD = {}
# Build bts numbers dict
btD = {'n_blindY_neg' : Counter(blind_test_target)[0]
, 'n_blindY_pos' : Counter(blind_test_target)[1]
, 'n_testY_ratio' : round(Counter(blind_test_target)[0]/Counter(blind_test_target)[1], 2)
, 'n_test_size' : len(blind_test_df) }
# Update cmD+tnD dicts with btD
mm_skf_scoresD[model_name].update(btD)
#--------------------------------------------------------
# Build the final results with all scores for the model
#--------------------------------------------------------
#bts_predict = gscv_fs.predict(blind_test_df)
model_pipeline.fit(input_df, target)
bts_predict = model_pipeline.predict(blind_test_df)
bts_mcc_score = round(matthews_corrcoef(blind_test_target, bts_predict),2)
print('\nMCC on Blind test:' , bts_mcc_score)
#print('\nAccuracy on Blind test:', round(accuracy_score(blind_test_target, bts_predict),2))
print('\nMCC on Training:' , mm_skf_scoresD[model_name]['test_mcc'] )
mm_skf_scoresD[model_name]['bts_mcc'] = bts_mcc_score
mm_skf_scoresD[model_name]['bts_fscore'] = round(f1_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_precision'] = round(precision_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_recall'] = round(recall_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_accuracy'] = round(accuracy_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_roc_auc'] = round(roc_auc_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_jcc'] = round(jaccard_score(blind_test_target, bts_predict),2)
#mm_skf_scoresD[model_name]['diff_mcc'] = train_test_diff_MCC
#return(mm_skf_scoresD)
#============================
# Process the dict to have WF
#============================
if return_formatted_output:
CV_BT_metaDF = ProcessMultModelsCl(mm_skf_scoresD)
return(CV_BT_metaDF)
else:
return(mm_skf_scoresD)
#%% Process output function ###################################################
############################
# ProcessMultModelsCl()
############################
#Processes the dict from above if use_formatted_output = True
def ProcessMultModelsCl(inputD = {}, blind_test_data = True):
scoresDF = pd.DataFrame(inputD)
#------------------------
# Extracting split_name
#-----------------------
tts_split_nameL = []
for k,v in inputD.items():
tts_split_nameL = tts_split_nameL + [v['tts_split']]
if len(set(tts_split_nameL)) == 1:
tts_split_name = str(list(set(tts_split_nameL))[0])
print('\nExtracting tts_split_name:', tts_split_name)
#----------------------
# WF: CV results
#----------------------
scoresDFT = scoresDF.T
scoresDF_CV = scoresDFT.filter(regex='^test_.*$', axis = 1); scoresDF_CV.columns
# map colnames for consistency to allow concatenting
scoresDF_CV.columns = scoresDF_CV.columns.map(scoreCV_mapD); scoresDF_CV.columns
scoresDF_CV['source_data'] = 'CV'
#----------------------
# WF: Meta data
#----------------------
metaDF = scoresDFT.filter(regex='^(?!test_.*$|bts_.*$|train_.*$).*'); metaDF.columns
print('\nTotal cols in each df:'
, '\nCV df:', len(scoresDF_CV.columns)
, '\nmetaDF:', len(metaDF.columns))
#-------------------------------------
# Combine WF: CV + Metadata
#-------------------------------------
combDF = pd.merge(scoresDF_CV, metaDF, left_index = True, right_index = True)
print('\nAdding column: Model_name')
combDF['Model_name'] = combDF.index
#----------------------
# WF: BTS results
#----------------------
if blind_test_data:
scoresDF_BT = scoresDFT.filter(regex='^bts_.*$', axis = 1); scoresDF_BT.columns
# map colnames for consistency to allow concatenting
scoresDF_BT.columns = scoresDF_BT.columns.map(scoreBT_mapD); scoresDF_BT.columns
scoresDF_BT['source_data'] = 'BT'
print('\nTotal cols in bts df:'
, '\nBT_df:', len(scoresDF_BT.columns))
if len(scoresDF_CV.columns) == len(scoresDF_BT.columns):
print('\nFirst proceeding to rowbind CV and BT dfs:')
expected_ncols_out = len(scoresDF_BT.columns) + len(metaDF.columns)
print('\nFinal output should have:', expected_ncols_out, 'columns' )
#-----------------
# Combine WF
#-----------------
dfs_combine_wf = [scoresDF_CV, scoresDF_BT]
print('\nCombinig', len(dfs_combine_wf), 'using pd.concat by row ~ rowbind'
, '\nChecking Dims of df to combine:'
, '\nDim of CV:', scoresDF_CV.shape
, '\nDim of BT:', scoresDF_BT.shape)
#print(scoresDF_CV)
#print(scoresDF_BT)
dfs_nrows_wf = []
for df in dfs_combine_wf:
dfs_nrows_wf = dfs_nrows_wf + [len(df)]
dfs_nrows_wf = max(dfs_nrows_wf)
dfs_ncols_wf = []
for df in dfs_combine_wf:
dfs_ncols_wf = dfs_ncols_wf + [len(df.columns)]
dfs_ncols_wf = max(dfs_ncols_wf)
print(dfs_ncols_wf)
expected_nrows_wf = len(dfs_combine_wf) * dfs_nrows_wf
expected_ncols_wf = dfs_ncols_wf
common_cols_wf = list(set.intersection(*(set(df.columns) for df in dfs_combine_wf)))
print('\nNumber of Common columns:', dfs_ncols_wf
, '\nThese are:', common_cols_wf)
if len(common_cols_wf) == dfs_ncols_wf :
combined_baseline_wf = pd.concat([df[common_cols_wf] for df in dfs_combine_wf], ignore_index=False)
print('\nConcatenating dfs with different resampling methods [WF]:'
, '\nSplit type:', tts_split_name
, '\nNo. of dfs combining:', len(dfs_combine_wf))
#print('\n================================================^^^^^^^^^^^^')
if len(combined_baseline_wf) == expected_nrows_wf and len(combined_baseline_wf.columns) == expected_ncols_wf:
#print('\n================================================^^^^^^^^^^^^')
print('\nPASS:', len(dfs_combine_wf), 'dfs successfully combined'
, '\nnrows in combined_df_wf:', len(combined_baseline_wf)
, '\nncols in combined_df_wf:', len(combined_baseline_wf.columns))
else:
print('\nFAIL: concatenating failed'
, '\nExpected nrows:', expected_nrows_wf
, '\nGot:', len(combined_baseline_wf)
, '\nExpected ncols:', expected_ncols_wf
, '\nGot:', len(combined_baseline_wf.columns))
sys.exit('\nFIRST IF FAILS')
##
c1L = list(set(combined_baseline_wf.index))
c2L = list(metaDF.index)
#if set(c1L) == set(c2L):
if set(c1L) == set(c2L) and all(x in c2L for x in c1L) and all(x in c1L for x in c2L):
print('\nPASS: proceeding to merge metadata with CV and BT dfs')
combDF = pd.merge(combined_baseline_wf, metaDF, left_index = True, right_index = True)
print('\nAdding column: Model_name')
combDF['Model_name'] = combDF.index
else:
sys.exit('\nFAIL: Could not merge metadata with CV and BT dfs')
else:
print('\nConcatenting dfs not possible [WF],check numbers ')
#-------------------------------------
# Combine WF+Metadata: Final output
#-------------------------------------
# if len(combDF.columns) == expected_ncols_out:
# print('\nPASS: Combined df has expected ncols')
# else:
# sys.exit('\nFAIL: Length mismatch for combined_df')
# print('\nAdding column: Model_name')
# combDF['Model_name'] = combDF.index
print('\n========================================================='
, '\nSUCCESS: Ran multiple classifiers'
, '\n=======================================================')
#resampling_methods_wf = combined_baseline_wf[['resampling']]
#resampling_methods_wf = resampling_methods_wf.drop_duplicates()
#, '\n', resampling_methods_wf)
return combDF
###############################################################################

306
scripts/ml/ml_functions/MultClfs_fi.py
View file

@ -1,306 +0,0 @@
#!/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 import datasets
from collections import Counter
from sklearn.linear_model import LogisticRegression, LogisticRegressionCV
from sklearn.linear_model import RidgeClassifier, RidgeClassifierCV, SGDClassifier, PassiveAggressiveClassifier
from sklearn.naive_bayes import BernoulliNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier, ExtraTreeClassifier
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier, AdaBoostClassifier, GradientBoostingClassifier, BaggingClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.gaussian_process import GaussianProcessClassifier, kernels
from sklearn.gaussian_process.kernels import RBF, DotProduct, Matern, RationalQuadratic, WhiteKernel
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis, QuadraticDiscriminantAnalysis
from sklearn.neural_network import MLPClassifier
from sklearn.svm import SVC
from xgboost import XGBClassifier
from sklearn.naive_bayes import MultinomialNB
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.compose import make_column_transformer
from sklearn.metrics import make_scorer, confusion_matrix, accuracy_score, balanced_accuracy_score, precision_score, average_precision_score, recall_score
from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef, jaccard_score, classification_report
# added
from sklearn.model_selection import train_test_split, cross_validate, cross_val_score, LeaveOneOut, KFold, RepeatedKFold, cross_val_predict
from sklearn.model_selection import train_test_split, cross_validate, cross_val_score
from sklearn.model_selection import StratifiedKFold,RepeatedStratifiedKFold, RepeatedKFold
from sklearn.pipeline import Pipeline, make_pipeline
from sklearn.feature_selection import RFE, RFECV
import itertools
import seaborn as sns
import matplotlib.pyplot as plt
from statistics import mean, stdev, median, mode
from imblearn.over_sampling import RandomOverSampler
from imblearn.under_sampling import RandomUnderSampler
from imblearn.over_sampling import SMOTE
from sklearn.datasets import make_classification
from imblearn.combine import SMOTEENN
from imblearn.combine import SMOTETomek
from imblearn.over_sampling import SMOTENC
from imblearn.under_sampling import EditedNearestNeighbours
from imblearn.under_sampling import RepeatedEditedNearestNeighbours
from sklearn.model_selection import GridSearchCV
from sklearn.base import BaseEstimator
from sklearn.impute import KNNImputer as KNN
import json
import argparse
import re
from sklearn.model_selection import LeaveOneGroupOut
#%% GLOBALS
rs = {'random_state': 42}
njobs = {'n_jobs': os.cpu_count() } # the number of jobs should equal the number of CPU cores
scoring_fn = ({ 'mcc' : make_scorer(matthews_corrcoef)
, 'fscore' : make_scorer(f1_score)
, 'precision' : make_scorer(precision_score)
, 'recall' : make_scorer(recall_score)
, 'accuracy' : make_scorer(accuracy_score)
, 'roc_auc' : make_scorer(roc_auc_score)
, 'jcc' : make_scorer(jaccard_score)
})
skf_cv = StratifiedKFold(n_splits = 10
#, shuffle = False, random_state= None)
, shuffle = True,**rs)
rskf_cv = RepeatedStratifiedKFold(n_splits = 10
, n_repeats = 3
, **rs)
logo = LeaveOneGroupOut()
mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
###############################################################################
homedir = os.path.expanduser("~")
sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml/ml_functions')
sys.path
###############################################################################
outdir = homedir
from GetMLData import *
from SplitTTS import *
def remove(string):
return(string.replace(" ", ""))
#%%############################################################################
############################
# MultModelsCl()
# Run Multiple Classifiers
############################
# Multiple Classification - Model Pipeline
def MultClfs_fi(input_df, target, sel_cv
, blind_test_df
, blind_test_target
, tts_split_type
, resampling_type = 'none' # default
#, add_cm = True # adds confusion matrix based on cross_val_predict
#, add_yn = True # adds target var class numbers
, var_type = ['numerical', 'categorical','mixed']
, run_blind_test = True
#, return_formatted_output = True
):
'''
@ param input_df: input features
@ type: df with input features WITHOUT the target variable
@param target: target (or output) feature
@type: df or np.array or Series
@param skv_cv: stratifiedK fold int or object to allow shuffle and random state to pass
@type: int or StratifiedKfold()
@var_type: numerical, categorical and mixed to determine what col_transform to apply (MinMaxScalar and/or one-ho t encoder)
@type: list
returns
Dict containing multiple classification scores for each model and mean of each Stratified Kfold including training
'''
#======================================================
# 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 = [('num', MinMaxScaler(), numerical_ix)
, ('cat', OneHotEncoder(), categorical_ix) ]
col_transform = ColumnTransformer(transformers = t
, remainder='passthrough')
#======================================================
# Specify multiple Classification Models
#======================================================
models = [('AdaBoost Classifier' , AdaBoostClassifier(**rs) )
# , ('Bagging Classifier' , BaggingClassifier(**rs, **njobs, bootstrap = True, oob_score = True) )
# , ('Decision Tree' , DecisionTreeClassifier(**rs) )
# , ('Extra Tree' , ExtraTreeClassifier(**rs) )
# , ('Extra Trees' , ExtraTreesClassifier(**rs) )
# , ('Gradient Boosting' , GradientBoostingClassifier(**rs) )
# , ('Gaussian NB' , GaussianNB() )
# , ('Gaussian Process' , GaussianProcessClassifier(**rs) )
# , ('K-Nearest Neighbors' , KNeighborsClassifier() )
# , ('LDA' , LinearDiscriminantAnalysis() )
# , ('Logistic Regression' , LogisticRegression(**rs) )
# , ('Logistic RegressionCV' , LogisticRegressionCV(cv = 3, **rs))
# , ('MLP' , MLPClassifier(max_iter = 500, **rs) )
# , ('Multinomial' , MultinomialNB() )
# , ('Naive Bayes' , BernoulliNB() )
# , ('Passive Aggresive' , PassiveAggressiveClassifier(**rs, **njobs) )
# , ('QDA' , QuadraticDiscriminantAnalysis() )
# , ('Random Forest' , RandomForestClassifier(**rs, n_estimators = 1000, **njobs ) )
# # , ('Random Forest2' , RandomForestClassifier(min_samples_leaf = 5
# # , n_estimators = 1000
# # , bootstrap = True
# # , oob_score = True
# # , **njobs
# # , **rs
# # , max_features = 'auto') )
# , ('Ridge Classifier' , RidgeClassifier(**rs) )
# , ('Ridge ClassifierCV' , RidgeClassifierCV(cv = 3) )
# , ('SVC' , SVC(**rs) )
, ('Stochastic GDescent' , SGDClassifier(**rs, **njobs) )
, ('XGBoost' , XGBClassifier(**rs, verbosity = 0, use_label_encoder =False, **njobs) )
]
mm_skf_scoresD = {}
print('\n==============================================================\n'
, '\nRunning several classification models (n):', len(models)
,'\nList of models:')
for m in models:
print(m)
print('\n================================================================\n')
index = 1
for model_name, model_fn in models:
print('\nRunning classifier:', index
, '\nModel_name:' , model_name
, '\nModel func:' , model_fn)
index = index+1
model_pipeline = Pipeline([
('prep' , col_transform)
, ('model' , model_fn)])
print('\nRunning model pipeline:', model_pipeline)
skf_cv_modD = cross_validate(model_pipeline
, input_df
, target
, cv = sel_cv
, scoring = scoring_fn)
#==============================
# Extract mean values for CV
#==============================
mm_skf_scoresD[model_name] = {}
for key, value in skf_cv_modD.items():
print('\nkey:', key, '\nvalue:', value)
print('\nmean value:', np.mean(value))
mm_skf_scoresD[model_name][key] = round(np.mean(value),2)
# ADD more info: meta data related to input df
mm_skf_scoresD[model_name]['resampling'] = resampling_type
mm_skf_scoresD[model_name]['n_training_size'] = len(input_df)
mm_skf_scoresD[model_name]['n_trainingY_ratio'] = round(Counter(target)[0]/Counter(target)[1], 2)
mm_skf_scoresD[model_name]['n_features'] = len(input_df.columns)
mm_skf_scoresD[model_name]['tts_split'] = tts_split_type
# FS
#mnf = remove(model_name)
#model_pipeline.fit(input_df, target)
#print('\nFeature importance:', (model_pipeline.named_steps.model.feature_importances_))
#allf_xgboost = model_pipeline.feature_names_in_
#fsi_model = model_pipeline.named_steps.model.feature_importances_
#mm_skf_scoresD[model_name]['fs_importance'] = fsi_model
# TODO: add this as a key
#Add
#pyplot.bar(range(len(model_pipeline.named_steps.model.feature_importances_)), model_pipeline.named_steps.model.feature_importances_)
#pyplot.show()
#plot_importance(model_pipeline.named_steps.model.feature_importances_)
#pyplot.show()
if run_blind_test:
btD = {}
# Build bts numbers dict
btD = {'n_blindY_neg' : Counter(blind_test_target)[0]
, 'n_blindY_pos' : Counter(blind_test_target)[1]
, 'n_testY_ratio' : round(Counter(blind_test_target)[0]/Counter(blind_test_target)[1], 2)
, 'n_test_size' : len(blind_test_df) }
# Update cmD+tnD dicts with btD
mm_skf_scoresD[model_name].update(btD)
#--------------------------------------------------------
# Build the final results with all scores for the model
#--------------------------------------------------------
#bts_predict = gscv_fs.predict(blind_test_df)
model_pipeline.fit(input_df, target)
bts_predict = model_pipeline.predict(blind_test_df)
bts_mcc_score = round(matthews_corrcoef(blind_test_target, bts_predict),2)
print('\nMCC on Blind test:' , bts_mcc_score)
#print('\nAccuracy on Blind test:', round(accuracy_score(blind_test_target, bts_predict),2))
mm_skf_scoresD[model_name]['bts_mcc'] = bts_mcc_score
mm_skf_scoresD[model_name]['bts_fscore'] = round(f1_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_precision'] = round(precision_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_recall'] = round(recall_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_accuracy'] = round(accuracy_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_roc_auc'] = round(roc_auc_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_jcc'] = round(jaccard_score(blind_test_target, bts_predict),2)
return(mm_skf_scoresD)
#%%

528
scripts/ml/ml_functions/MultClfs_logo.py
View file

@ -1,528 +0,0 @@
#!/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 import datasets
from collections import Counter
from sklearn.linear_model import LogisticRegression, LogisticRegressionCV
from sklearn.linear_model import RidgeClassifier, RidgeClassifierCV, SGDClassifier, PassiveAggressiveClassifier
from sklearn.naive_bayes import BernoulliNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier, ExtraTreeClassifier
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier, AdaBoostClassifier, GradientBoostingClassifier, BaggingClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.gaussian_process import GaussianProcessClassifier, kernels
from sklearn.gaussian_process.kernels import RBF, DotProduct, Matern, RationalQuadratic, WhiteKernel
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis, QuadraticDiscriminantAnalysis
from sklearn.neural_network import MLPClassifier
from sklearn.svm import SVC
from xgboost import XGBClassifier
from sklearn.naive_bayes import MultinomialNB
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.compose import make_column_transformer
from sklearn.metrics import make_scorer, confusion_matrix, accuracy_score, balanced_accuracy_score, precision_score, average_precision_score, recall_score
from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef, jaccard_score, classification_report
# added
from sklearn.model_selection import train_test_split, cross_validate, cross_val_score, LeaveOneOut, KFold, RepeatedKFold, cross_val_predict
from sklearn.model_selection import train_test_split, cross_validate, cross_val_score
from sklearn.model_selection import StratifiedKFold,RepeatedStratifiedKFold, RepeatedKFold
from sklearn.pipeline import Pipeline, make_pipeline
from sklearn.feature_selection import RFE, RFECV
import itertools
import seaborn as sns
import matplotlib.pyplot as plt
from statistics import mean, stdev, median, mode
from imblearn.over_sampling import RandomOverSampler
from imblearn.under_sampling import RandomUnderSampler
from imblearn.over_sampling import SMOTE
from sklearn.datasets import make_classification
from imblearn.combine import SMOTEENN
from imblearn.combine import SMOTETomek
from imblearn.over_sampling import SMOTENC
from imblearn.under_sampling import EditedNearestNeighbours
from imblearn.under_sampling import RepeatedEditedNearestNeighbours
from sklearn.model_selection import GridSearchCV
from sklearn.base import BaseEstimator
from sklearn.impute import KNNImputer as KNN
import json
import argparse
import re
import itertools
from sklearn.model_selection import LeaveOneGroupOut
#%% GLOBALS
rs = {'random_state': 42}
njobs = {'n_jobs': os.cpu_count() } # the number of jobs should equal the number of CPU cores
scoring_fn = ({ 'mcc' : make_scorer(matthews_corrcoef)
, 'fscore' : make_scorer(f1_score)
, 'precision' : make_scorer(precision_score)
, 'recall' : make_scorer(recall_score)
, 'accuracy' : make_scorer(accuracy_score)
, 'roc_auc' : make_scorer(roc_auc_score)
, 'jcc' : make_scorer(jaccard_score)
})
skf_cv = StratifiedKFold(n_splits = 10
#, shuffle = False, random_state= None)
, shuffle = True,**rs)
rskf_cv = RepeatedStratifiedKFold(n_splits = 10
, n_repeats = 3
, **rs)
logo = LeaveOneGroupOut()
mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
###############################################################################
score_type_ordermapD = { 'mcc' : 1
, 'fscore' : 2
, 'jcc' : 3
, 'precision' : 4
, 'recall' : 5
, 'accuracy' : 6
, 'roc_auc' : 7
, 'TN' : 8
, 'FP' : 9
, 'FN' : 10
, 'TP' : 11
, 'trainingY_neg': 12
, 'trainingY_pos': 13
, 'blindY_neg' : 14
, 'blindY_pos' : 15
, 'fit_time' : 16
, 'score_time' : 17
}
scoreCV_mapD = {'test_mcc' : 'MCC'
, 'test_fscore' : 'F1'
, 'test_precision' : 'Precision'
, 'test_recall' : 'Recall'
, 'test_accuracy' : 'Accuracy'
, 'test_roc_auc' : 'ROC_AUC'
, 'test_jcc' : 'JCC'
}
scoreBT_mapD = {'bts_mcc' : 'MCC'
, 'bts_fscore' : 'F1'
, 'bts_precision' : 'Precision'
, 'bts_recall' : 'Recall'
, 'bts_accuracy' : 'Accuracy'
, 'bts_roc_auc' : 'ROC_AUC'
, 'bts_jcc' : 'JCC'
}
#gene_group = 'gene_name'
#%%############################################################################
############################
# MultModelsCl()
# Run Multiple Classifiers
############################
# Multiple Classification - Model Pipeline
def MultModelsCl_logo(input_df
, target
, sel_cv
, blind_test_df = pd.DataFrame()
, blind_test_target = pd.Series(dtype = int)
, tts_split_type = "none"
, group = 'none'
, resampling_type = 'none' # default
, add_cm = True # adds confusion matrix based on cross_val_predict
, add_yn = True # adds target var class numbers
, var_type = ['numerical', 'categorical','mixed']
, run_blind_test = True
, return_formatted_output = True):
'''
@ param input_df: input features
@ type: df with input features WITHOUT the target variable
@param target: target (or output) feature
@type: df or np.array or Series
@param skv_cv: stratifiedK fold int or object to allow shuffle and random state to pass
@type: int or StratifiedKfold()
@var_type: numerical, categorical and mixed to determine what col_transform to apply (MinMaxScalar and/or one-ho t encoder)
@type: list
returns
Dict containing multiple classification scores for each model and mean of each Stratified Kfold including training
'''
# if group == 'none':
# sel_cv = skf_cv
# else:
# group = 'none'
#======================================================
# 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 = [('num', MinMaxScaler(), numerical_ix)
, ('cat', OneHotEncoder(), categorical_ix) ]
col_transform = ColumnTransformer(transformers = t
, remainder='passthrough')
#======================================================
# Specify multiple Classification Models
#======================================================
models = [('AdaBoost Classifier' , AdaBoostClassifier(**rs) )
, ('Bagging Classifier' , BaggingClassifier(**rs, **njobs, bootstrap = True, oob_score = True) )
, ('Decision Tree' , DecisionTreeClassifier(**rs) )
, ('Extra Tree' , ExtraTreeClassifier(**rs) )
, ('Extra Trees' , ExtraTreesClassifier(**rs) )
, ('Gradient Boosting' , GradientBoostingClassifier(**rs) )
, ('Gaussian NB' , GaussianNB() )
, ('Gaussian Process' , GaussianProcessClassifier(**rs) )
, ('K-Nearest Neighbors' , KNeighborsClassifier() )
, ('LDA' , LinearDiscriminantAnalysis() )
, ('Logistic Regression' , LogisticRegression(**rs) )
, ('Logistic RegressionCV' , LogisticRegressionCV(cv = 3, **rs))
, ('MLP' , MLPClassifier(max_iter = 500, **rs) )
, ('Multinomial' , MultinomialNB() )
, ('Naive Bayes' , BernoulliNB() )
, ('Passive Aggresive' , PassiveAggressiveClassifier(**rs, **njobs) )
, ('QDA' , QuadraticDiscriminantAnalysis() )
, ('Random Forest' , RandomForestClassifier(**rs, n_estimators = 1000 ) )
, ('Random Forest2' , RandomForestClassifier(min_samples_leaf = 5
, n_estimators = 1000
, bootstrap = True
, oob_score = True
, **njobs
, **rs
, max_features = 'auto') )
, ('Ridge Classifier' , RidgeClassifier(**rs) )
, ('Ridge ClassifierCV' , RidgeClassifierCV(cv = 3) )
, ('SVC' , SVC(**rs) )
, ('Stochastic GDescent' , SGDClassifier(**rs, **njobs) )
, ('XGBoost' , XGBClassifier(**rs, verbosity = 0, use_label_encoder =False) )
]
mm_skf_scoresD = {}
print('\n==============================================================\n'
, '\nRunning several classification models (n):', len(models)
,'\nList of models:')
for m in models:
print(m)
print('\n================================================================\n')
index = 1
for model_name, model_fn in models:
print('\nRunning classifier:', index
, '\nModel_name:' , model_name
, '\nModel func:' , model_fn)
index = index+1
model_pipeline = Pipeline([
('prep' , col_transform)
, ('model' , model_fn)])
print('\nRunning model pipeline:', model_pipeline)
cv_modD = cross_validate(model_pipeline
, input_df
, target
, cv = sel_cv
, groups = group
, scoring = scoring_fn
, return_train_score = True)
#==============================
# Extract mean values for CV
#==============================
mm_skf_scoresD[model_name] = {}
for key, value in cv_modD.items():
print('\nkey:', key, '\nvalue:', value)
print('\nmean value:', np.mean(value))
mm_skf_scoresD[model_name][key] = round(np.mean(value),2)
# ADD more info: meta data related to input df
mm_skf_scoresD[model_name]['resampling'] = resampling_type
mm_skf_scoresD[model_name]['n_training_size'] = len(input_df)
mm_skf_scoresD[model_name]['n_trainingY_ratio'] = round(Counter(target)[0]/Counter(target)[1], 2)
mm_skf_scoresD[model_name]['n_features'] = len(input_df.columns)
mm_skf_scoresD[model_name]['tts_split'] = tts_split_type
#######################################################################
#======================================================
# Option: Add confusion matrix from cross_val_predict
# Understand and USE with caution
#======================================================
if add_cm:
cmD = {}
# Calculate cm
y_pred = cross_val_predict(model_pipeline, input_df, target, cv = sel_cv, groups = group, **njobs)
#_tn, _fp, _fn, _tp = confusion_matrix(y_pred, y).ravel() # internally
tn, fp, fn, tp = confusion_matrix(y_pred, target).ravel()
# Build cm dict
cmD = {'TN' : tn
, 'FP': fp
, 'FN': fn
, 'TP': tp}
# Update cv dict cmD
mm_skf_scoresD[model_name].update(cmD)
#=============================================
# Option: Add targety numbers for data
#=============================================
if add_yn:
tnD = {}
# Build tn numbers dict
tnD = {'n_trainingY_neg' : Counter(target)[0]
, 'n_trainingY_pos' : Counter(target)[1] }
# Update cv dict with cmD and tnD
mm_skf_scoresD[model_name].update(tnD)
#%%
#=========================
# Option: Blind test (bts)
#=========================
if run_blind_test:
btD = {}
# Build bts numbers dict
btD = {'n_blindY_neg' : Counter(blind_test_target)[0]
, 'n_blindY_pos' : Counter(blind_test_target)[1]
, 'n_testY_ratio' : round(Counter(blind_test_target)[0]/Counter(blind_test_target)[1], 2)
, 'n_test_size' : len(blind_test_df) }
# Update cmD+tnD dicts with btD
mm_skf_scoresD[model_name].update(btD)
#--------------------------------------------------------
# Build the final results with all scores for the model
#--------------------------------------------------------
#bts_predict = gscv_fs.predict(blind_test_df)
model_pipeline.fit(input_df, target)
bts_predict = model_pipeline.predict(blind_test_df)
bts_mcc_score = round(matthews_corrcoef(blind_test_target, bts_predict),2)
print('\nMCC on Blind test:' , bts_mcc_score)
print('\nAccuracy on Blind test:', round(accuracy_score(blind_test_target, bts_predict),2))
mm_skf_scoresD[model_name]['bts_mcc'] = bts_mcc_score
mm_skf_scoresD[model_name]['bts_fscore'] = round(f1_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_precision'] = round(precision_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_recall'] = round(recall_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_accuracy'] = round(accuracy_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_roc_auc'] = round(roc_auc_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_jcc'] = round(jaccard_score(blind_test_target, bts_predict),2)
#mm_skf_scoresD[model_name]['diff_mcc'] = train_test_diff_MCC
#return(mm_skf_scoresD)
#============================
# Process the dict to have WF
#============================
if return_formatted_output:
CV_BT_metaDF = ProcessMultModelsCl(mm_skf_scoresD)
return(CV_BT_metaDF)
else:
return(mm_skf_scoresD)
#%% Process output function ###################################################
############################
# ProcessMultModelsCl()
############################
#Processes the dict from above if use_formatted_output = True
def ProcessMultModelsCl(inputD = {}
, blind_test_data = True):
scoresDF = pd.DataFrame(inputD)
#------------------------
# Extracting split_name
#-----------------------
tts_split_nameL = []
for k,v in inputD.items():
tts_split_nameL = tts_split_nameL + [v['tts_split']]
if len(set(tts_split_nameL)) == 1:
tts_split_name = str(list(set(tts_split_nameL))[0])
print('\nExtracting tts_split_name:', tts_split_name)
#----------------------
# WF: CV results
#----------------------
scoresDFT = scoresDF.T
scoresDF_CV = scoresDFT.filter(regex='^test_.*$', axis = 1); scoresDF_CV.columns
# map colnames for consistency to allow concatenting
scoresDF_CV.columns = scoresDF_CV.columns.map(scoreCV_mapD); scoresDF_CV.columns
scoresDF_CV['source_data'] = 'CV'
#----------------------
# WF: Meta data
#----------------------
metaDF = scoresDFT.filter(regex='^(?!test_.*$|bts_.*$|train_.*$).*'); metaDF.columns
print('\nTotal cols in each df:'
, '\nCV df:', len(scoresDF_CV.columns)
, '\nmetaDF:', len(metaDF.columns))
#-------------------------------------
# Combine WF: CV + Metadata
#-------------------------------------
combDF = pd.merge(scoresDF_CV, metaDF, left_index = True, right_index = True)
print('\nAdding column: Model_name')
combDF['Model_name'] = combDF.index
#----------------------
# WF: BTS results
#----------------------
if blind_test_data:
scoresDF_BT = scoresDFT.filter(regex='^bts_.*$', axis = 1); scoresDF_BT.columns
# map colnames for consistency to allow concatenting
scoresDF_BT.columns = scoresDF_BT.columns.map(scoreBT_mapD); scoresDF_BT.columns
scoresDF_BT['source_data'] = 'BT'
print('\nTotal cols in bts df:'
, '\nBT_df:', len(scoresDF_BT.columns))
if len(scoresDF_CV.columns) == len(scoresDF_BT.columns):
print('\nFirst proceeding to rowbind CV and BT dfs:')
expected_ncols_out = len(scoresDF_BT.columns) + len(metaDF.columns)
print('\nFinal output should have:', expected_ncols_out, 'columns' )
#-----------------
# Combine WF
#-----------------
dfs_combine_wf = [scoresDF_CV, scoresDF_BT]
print('\nCombinig', len(dfs_combine_wf), 'using pd.concat by row ~ rowbind'
, '\nChecking Dims of df to combine:'
, '\nDim of CV:', scoresDF_CV.shape
, '\nDim of BT:', scoresDF_BT.shape)
#print(scoresDF_CV)
#print(scoresDF_BT)
dfs_nrows_wf = []
for df in dfs_combine_wf:
dfs_nrows_wf = dfs_nrows_wf + [len(df)]
dfs_nrows_wf = max(dfs_nrows_wf)
dfs_ncols_wf = []
for df in dfs_combine_wf:
dfs_ncols_wf = dfs_ncols_wf + [len(df.columns)]
dfs_ncols_wf = max(dfs_ncols_wf)
print(dfs_ncols_wf)
expected_nrows_wf = len(dfs_combine_wf) * dfs_nrows_wf
expected_ncols_wf = dfs_ncols_wf
common_cols_wf = list(set.intersection(*(set(df.columns) for df in dfs_combine_wf)))
print('\nNumber of Common columns:', dfs_ncols_wf
, '\nThese are:', common_cols_wf)
if len(common_cols_wf) == dfs_ncols_wf :
combined_baseline_wf = pd.concat([df[common_cols_wf] for df in dfs_combine_wf], ignore_index=False)
print('\nConcatenating dfs with different resampling methods [WF]:'
, '\nSplit type:', tts_split_name
, '\nNo. of dfs combining:', len(dfs_combine_wf))
#print('\n================================================^^^^^^^^^^^^')
if len(combined_baseline_wf) == expected_nrows_wf and len(combined_baseline_wf.columns) == expected_ncols_wf:
#print('\n================================================^^^^^^^^^^^^')
print('\nPASS:', len(dfs_combine_wf), 'dfs successfully combined'
, '\nnrows in combined_df_wf:', len(combined_baseline_wf)
, '\nncols in combined_df_wf:', len(combined_baseline_wf.columns))
else:
print('\nFAIL: concatenating failed'
, '\nExpected nrows:', expected_nrows_wf
, '\nGot:', len(combined_baseline_wf)
, '\nExpected ncols:', expected_ncols_wf
, '\nGot:', len(combined_baseline_wf.columns))
sys.exit('\nFIRST IF FAILS')
##
c1L = list(set(combined_baseline_wf.index))
c2L = list(metaDF.index)
#if set(c1L) == set(c2L):
if set(c1L) == set(c2L) and all(x in c2L for x in c1L) and all(x in c1L for x in c2L):
print('\nPASS: proceeding to merge metadata with CV and BT dfs')
combDF = pd.merge(combined_baseline_wf, metaDF, left_index = True, right_index = True)
print('\nAdding column: Model_name')
combDF['Model_name'] = combDF.index
else:
sys.exit('\nFAIL: Could not merge metadata with CV and BT dfs')
else:
# print('\nConcatenting dfs not possible [WF],check numbers ')
print('\nOnly combining CV and metadata')
#-------------------------------------
# Combine WF+Metadata: Final output
#-------------------------------------
# if len(combDF.columns) == expected_ncols_out:
# print('\nPASS: Combined df has expected ncols')
# else:
# sys.exit('\nFAIL: Length mismatch for combined_df')
# print('\nAdding column: Model_name')
# combDF['Model_name'] = combDF.index
print('\n========================================================='
, '\nSUCCESS: Ran multiple classifiers'
, '\n=======================================================')
#resampling_methods_wf = combined_baseline_wf[['resampling']]
#resampling_methods_wf = resampling_methods_wf.drop_duplicates()
#, '\n', resampling_methods_wf)
return combDF
###############################################################################

21
scripts/ml/ml_functions/MultClfs_logo_skf.py
View file

@ -77,9 +77,11 @@ import re
import itertools import itertools
from sklearn.model_selection import LeaveOneGroupOut from sklearn.model_selection import LeaveOneGroupOut
from sklearn.decomposition import PCA from sklearn.decomposition import PCA
from sklearn.naive_bayes import ComplementNB
from sklearn.dummy import DummyClassifier
#%% GLOBALS #%% GLOBALS
#rs = {'random_state': 42} #rs = {'random_state': 42} # INSIDE FUNCTION CALL NOW
#njobs = {'n_jobs': os.cpu_count() } # the number of jobs should equal the number of CPU cores #njobs = {'n_jobs': os.cpu_count() } # the number of jobs should equal the number of CPU cores
scoring_fn = ({ 'mcc' : make_scorer(matthews_corrcoef) scoring_fn = ({ 'mcc' : make_scorer(matthews_corrcoef)
@ -90,8 +92,7 @@ scoring_fn = ({ 'mcc' : make_scorer(matthews_corrcoef)
, 'roc_auc' : make_scorer(roc_auc_score) , 'roc_auc' : make_scorer(roc_auc_score)
, 'jcc' : make_scorer(jaccard_score) , 'jcc' : make_scorer(jaccard_score)
}) })
# for sel_cv INSIDE FUNCTION CALL NOW
# for sel_cv
#skf_cv = StratifiedKFold(n_splits = 10 #skf_cv = StratifiedKFold(n_splits = 10
# #, shuffle = False, random_state= None) # #, shuffle = False, random_state= None)
# , shuffle = True, **rs) # , shuffle = True, **rs)
@ -190,6 +191,14 @@ def MultModelsCl_logo_skf(input_df
rs = {'random_state': random_state} rs = {'random_state': random_state}
njobs = {'n_jobs': n_jobs} njobs = {'n_jobs': n_jobs}
skf_cv = StratifiedKFold(n_splits = 10
#, shuffle = False, random_state= None)
, shuffle = True,**rs)
rskf_cv = RepeatedStratifiedKFold(n_splits = 10
, n_repeats = 3
, **rs)
logo = LeaveOneGroupOut()
# select CV type: # select CV type:
# if group == None: # if group == None:
@ -254,6 +263,8 @@ def MultModelsCl_logo_skf(input_df
#====================================================== #======================================================
models = [('AdaBoost Classifier' , AdaBoostClassifier(**rs) ) models = [('AdaBoost Classifier' , AdaBoostClassifier(**rs) )
, ('Bagging Classifier' , BaggingClassifier(**rs, **njobs, bootstrap = True, oob_score = True, verbose = 3, n_estimators = 100) ) , ('Bagging Classifier' , BaggingClassifier(**rs, **njobs, bootstrap = True, oob_score = True, verbose = 3, n_estimators = 100) )
#, ('Bernoulli NB' , BernoulliNB() ) # pks Naive Bayes, CAUTION
, ('Complement NB' , ComplementNB() )
, ('Decision Tree' , DecisionTreeClassifier(**rs) ) , ('Decision Tree' , DecisionTreeClassifier(**rs) )
, ('Extra Tree' , ExtraTreeClassifier(**rs) ) , ('Extra Tree' , ExtraTreeClassifier(**rs) )
, ('Extra Trees' , ExtraTreesClassifier(**rs) ) , ('Extra Trees' , ExtraTreesClassifier(**rs) )
@ -265,8 +276,7 @@ def MultModelsCl_logo_skf(input_df
, ('Logistic Regression' , LogisticRegression(**rs) ) , ('Logistic Regression' , LogisticRegression(**rs) )
, ('Logistic RegressionCV' , LogisticRegressionCV(cv = 3, **rs)) , ('Logistic RegressionCV' , LogisticRegressionCV(cv = 3, **rs))
, ('MLP' , MLPClassifier(max_iter = 500, **rs) ) , ('MLP' , MLPClassifier(max_iter = 500, **rs) )
, ('Multinomial' , MultinomialNB() ) , ('Multinomial NB' , MultinomialNB() )
, ('Naive Bayes' , BernoulliNB() )
, ('Passive Aggresive' , PassiveAggressiveClassifier(**rs, **njobs) ) , ('Passive Aggresive' , PassiveAggressiveClassifier(**rs, **njobs) )
, ('QDA' , QuadraticDiscriminantAnalysis() ) , ('QDA' , QuadraticDiscriminantAnalysis() )
, ('Random Forest' , RandomForestClassifier(**rs, n_estimators = 1000, **njobs ) ) , ('Random Forest' , RandomForestClassifier(**rs, n_estimators = 1000, **njobs ) )
@ -282,6 +292,7 @@ def MultModelsCl_logo_skf(input_df
, ('SVC' , SVC(**rs) ) , ('SVC' , SVC(**rs) )
, ('Stochastic GDescent' , SGDClassifier(**rs, **njobs) ) , ('Stochastic GDescent' , SGDClassifier(**rs, **njobs) )
, ('XGBoost' , XGBClassifier(**rs, verbosity = 0, use_label_encoder = False, **njobs) ) , ('XGBoost' , XGBClassifier(**rs, verbosity = 0, use_label_encoder = False, **njobs) )
, ('Dummy Classifier' , DummyClassifier(strategy = 'most_frequent') )
] ]
mm_skf_scoresD = {} mm_skf_scoresD = {}