Skip to content

C
covid_analysis
Commit 553cf866 authored by Joaquin Torres's avatar Joaquin Torres
Browse files
Options

Basic structure for testing models

parent bb7d8177
Hide whitespace changes
Inline Side-by-side
Showing with 241 additions and 0 deletions
models/test_models.py 0 → 100644
View file @ 553cf866
"""
Evaluating optimized models with test data
"""
# Libraries
# --------------------------------------------------------------------------------------------------------
import pandas as pd
import numpy as np
from xgboost import XGBClassifier
from sklearn.metrics import confusion_matrix
from sklearn.metrics import f1_score, make_scorer, precision_score, recall_score, accuracy_score
from sklearn.ensemble import RandomForestClassifier, BaggingClassifier, AdaBoostClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.svm import SVC
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
# --------------------------------------------------------------------------------------------------------
# Reading test data
# --------------------------------------------------------------------------------------------------------
def read_test_data():
# Load test data
X_test_pre = np.load('../gen_train_data/data/output/pre/X_test_pre.npy', allow_pickle=True)
y_test_pre = np.load('../gen_train_data/data/output/pre/y_test_pre.npy', allow_pickle=True)
X_test_post = np.load('../gen_train_data/data/output/post/X_test_post.npy', allow_pickle=True)
y_test_post = np.load('../gen_train_data/data/output/post/y_test_post.npy', allow_pickle=True)
data_dic = {
"X_test_pre": X_test_pre,
"y_test_pre": y_test_pre,
"X_test_post": X_test_post,
"y_test_post": y_test_post,
}
return data_dic
# --------------------------------------------------------------------------------------------------------
# Returning tuned models for each situation
# --------------------------------------------------------------------------------------------------------
def get_tuned_models(group_id, method_id):
# 1. PRE
if group_id == 0:
# 1.1) Trained with original dataset
if method_id == 0:
tuned_models = {
"DT" : DecisionTreeClassifier(),
"RF" : RandomForestClassifier(),
"Bagging" : BaggingClassifier(),
"AB" : AdaBoostClassifier(),
"XGB": XGBClassifier(),
"LR" : LogisticRegression(max_iter=1000),
"ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'),
"SVM" : SVC(probability=True),
"MLP" : MLPClassifier(max_iter=500)
}
# 1.2) Trained with original dataset and cost-sensitive learning
elif method_id == 1:
tuned_models = {
"DT" : DecisionTreeClassifier(),
"RF" : RandomForestClassifier(),
"Bagging" : BaggingClassifier(),
"AB" : AdaBoostClassifier(),
"XGB": XGBClassifier(),
"LR" : LogisticRegression(max_iter=1000),
"ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'),
"SVM" : SVC(probability=True),
"MLP" : MLPClassifier(max_iter=500)
}
# 1.3) Trained with oversampled training dataset
elif method_id == 2:
tuned_models = {
"DT" : DecisionTreeClassifier(),
"RF" : RandomForestClassifier(),
"Bagging" : BaggingClassifier(),
"AB" : AdaBoostClassifier(),
"XGB": XGBClassifier(),
"LR" : LogisticRegression(max_iter=1000),
"ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'),
"SVM" : SVC(probability=True),
"MLP" : MLPClassifier(max_iter=500)
}
# 1. 4) Trained with undersampled training dataset
elif method_id == 3:
tuned_models = {
"DT" : DecisionTreeClassifier(),
"RF" : RandomForestClassifier(),
"Bagging" : BaggingClassifier(),
"AB" : AdaBoostClassifier(),
"XGB": XGBClassifier(),
"LR" : LogisticRegression(max_iter=1000),
"ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'),
"SVM" : SVC(probability=True),
"MLP" : MLPClassifier(max_iter=500)
}
# 2. POST
else:
# 2.1) Trained with original dataset
if method_id == 0:
tuned_models = {
"DT" : DecisionTreeClassifier(),
"RF" : RandomForestClassifier(),
"Bagging" : BaggingClassifier(),
"AB" : AdaBoostClassifier(),
"XGB": XGBClassifier(),
"LR" : LogisticRegression(max_iter=1000),
"ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'),
"SVM" : SVC(probability=True),
"MLP" : MLPClassifier(max_iter=500)
}
# 2.2) Trained with original dataset and cost-sensitive learning
elif method_id == 1:
tuned_models = {
"DT" : DecisionTreeClassifier(),
"RF" : RandomForestClassifier(),
"Bagging" : BaggingClassifier(),
"AB" : AdaBoostClassifier(),
"XGB": XGBClassifier(),
"LR" : LogisticRegression(max_iter=1000),
"ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'),
"SVM" : SVC(probability=True),
"MLP" : MLPClassifier(max_iter=500)
}
# 2.3) Trained with oversampled training dataset
elif method_id == 2:
tuned_models = {
"DT" : DecisionTreeClassifier(),
"RF" : RandomForestClassifier(),
"Bagging" : BaggingClassifier(),
"AB" : AdaBoostClassifier(),
"XGB": XGBClassifier(),
"LR" : LogisticRegression(max_iter=1000),
"ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'),
"SVM" : SVC(probability=True),
"MLP" : MLPClassifier(max_iter=500)
}
# 2.4) Trained with undersampled training dataset
elif method_id == 3:
tuned_models = {
"DT" : DecisionTreeClassifier(),
"RF" : RandomForestClassifier(),
"Bagging" : BaggingClassifier(),
"AB" : AdaBoostClassifier(),
"XGB": XGBClassifier(),
"LR" : LogisticRegression(max_iter=1000),
"ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'),
"SVM" : SVC(probability=True),
"MLP" : MLPClassifier(max_iter=500)
}
return tuned_models
# --------------------------------------------------------------------------------------------------------
# Scorers
# --------------------------------------------------------------------------------------------------------
def TN_scorer(clf, X, y):
"""Gives the number of samples predicted as true negatives"""
y_pred = clf.predict(X)
cm = confusion_matrix(y, y_pred)
TN = cm[0,0]
return TN
def FN_scorer(clf, X, y):
"""Gives the number of samples predicted as false negatives"""
y_pred = clf.predict(X)
cm = confusion_matrix(y, y_pred)
FN = cm[0,1]
return FN
def FP_scorer(clf, X, y):
"""Gives the number of samples predicted as false positive"""
y_pred = clf.predict(X)
cm = confusion_matrix(y, y_pred)
FP = cm[1,0]
return FP
def TP_scorer(clf, X, y):
"""Gives the number of samples predicted as true positive"""
y_pred = clf.predict(X)
cm = confusion_matrix(y, y_pred)
TP = cm[1,1]
return TP
def negative_recall_scorer(clf, X, y):
"""Gives the negative recall defined as the (number of true_negative_samples)/(total number of negative samples)"""
y_pred = clf.predict(X)
cm = confusion_matrix(y, y_pred)
TN_prop = cm[0,0]/(cm[0,1]+cm[0,0])
return TN_prop
# --------------------------------------------------------------------------------------------------------
if __name__ == "__main__":
# Reading testing data
data_dic = read_test_data()
# Setup
# --------------------------------------------------------------------------------------------------------
# Scorings to use for model evaluation
scorings = {
'F1':make_scorer(f1_score),
'NREC': negative_recall_scorer,
'REC':make_scorer(recall_score),
'PREC':make_scorer(precision_score),
'ACC': make_scorer(accuracy_score),
'TN':TN_scorer,
'FN':FN_scorer,
'FP':FP_scorer,
'TP':TP_scorer
# AUROC and AUPRC (plot?)
}
method_names = {
0: "ORIG",
1: "ORIG_CW",
2: "OVER",
3: "UNDER"
}
# --------------------------------------------------------------------------------------------------------
# Evaluating performance using test dataset
# --------------------------------------------------------------------------------------------------------
scores_sheets = {} # To store score dfs as sheets in the same excel file
for i, group in enumerate(['pre', 'post']):
# Get test dataset based on group
X = data_dic['X_test' + group]
y = data_dic['y_test' + group]
for j, method in enumerate(['', '', 'over_', 'under_']):
# Get tuned models for this group and method
models = get_tuned_models(group_id=i, method_id=j)
# Scores df
scores_df = pd.DataFrame(index=models.keys(), columns=scorings.keys())
# Evaluate each model
for model_name, model in models.items():
# At each of the scores of interest
for score_name, scorer in scorings.items():
score_value = scorer(model, X, y)
scores_df.at[model_name, score_name] = score_value
# Store the DataFrame in the dictionary with a unique key for each sheet
sheet_name = f"{group}_{method_names[j]}"
scores_sheets[sheet_name] = scores_df
# Write results to Excel file
with pd.ExcelWriter('./training_models/output/testing_tuned_models.xlsx') as writer:
for sheet_name, data in scores_sheets.items():
data.to_excel(writer, sheet_name=sheet_name)
# --------------------------------------------------------------------------------------------------------
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment