From ca1e73a76581d0367093908025447949ee7ed0bc Mon Sep 17 00:00:00 2001
From: Ludovic Moncla <moncla.ludovic@gmail.com>
Date: Sun, 10 Jul 2022 17:12:28 +0200
Subject: [PATCH] Delete bert_experiments.py
---
experiments/bert_experiments.py | 349 --------------------------------
1 file changed, 349 deletions(-)
delete mode 100644 experiments/bert_experiments.py
diff --git a/experiments/bert_experiments.py b/experiments/bert_experiments.py
deleted file mode 100644
index b4e4bcd..0000000
--- a/experiments/bert_experiments.py
+++ /dev/null
@@ -1,349 +0,0 @@
-import pandas as pd
-import numpy as np
-import torch
-import transformers as ppb
-from sklearn.model_selection import train_test_split
-from sklearn import preprocessing
-import statistics
-import os
-import sys
-import argparse
-import configparser
-from transformers import CamembertModel, CamembertTokenizer
-from transformers import FlaubertModel, FlaubertTokenizer
-
-
-from sklearn.svm import SVC
-from sklearn.tree import DecisionTreeClassifier
-from sklearn.ensemble import RandomForestClassifier
-from sklearn.linear_model import LogisticRegression
-from sklearn.linear_model import SGDClassifier
-from sklearn.neighbors import KNeighborsClassifier
-from sklearn.model_selection import GridSearchCV
-
-
-import matplotlib.pyplot as plt
-from sklearn.metrics import plot_confusion_matrix
-from sklearn.metrics import confusion_matrix
-from sklearn.metrics import classification_report
-import seaborn as sns
-
-
-
-
-
-
-def evaluate_model(clf, X_test, y_test, y_pred, valid_y, classes, classesName, pathSave):
-
- #classifier, label_list, test_x, valid_y, title = "Confusion matrix"):
- precision = []
- recall = []
- f1 = []
- support = []
- weighted_avg = None
- accuracy = None
-
- df = pd.DataFrame(columns= ['className', 'precision', 'recall', 'f1-score', 'support', 'FP', 'FN', 'TP', 'TN'])
- report = classification_report( y_pred, valid_y, output_dict = True)
- for c in classes:
- precision.append(report[c]['precision'])
- recall.append(report[c]['recall'])
- f1.append(report[c]['f1-score'])
- support.append(report[c]['support'])
-
- accuracy = report['accuracy']
- weighted_avg = report['weighted avg']
- cnf_matrix = confusion_matrix(valid_y, y_pred)
- FP = cnf_matrix.sum(axis=0) - np.diag(cnf_matrix)
- FN = cnf_matrix.sum(axis=1) - np.diag(cnf_matrix)
- TP = np.diag(cnf_matrix)
- TN = cnf_matrix.sum() - (FP + FN + TP)
-
- df['className'] = classesName
- df['precision'] = precision
- df['recall'] = recall
- df['f1-score'] = f1
- df['support'] = support
- df['FP'] = FP
- df['FN'] = FN
- df['TP'] = TP
- df['TN'] = TN
- #disp = plot_confusion_matrix(classifier, test_x, valid_y,
- # display_labels= label_list,
- # cmap=plt.cm.Blues,
- # normalize=None)
- #disp.ax_.set_title(title)
-
- #print(title)
- #print(disp.confusion_matrix)
-
- #plt.show()
- plt.rcParams["font.size"] = 3
- plot_confusion_matrix(clf, X_test, y_test)
- plt.savefig(pathSave)
- return df, accuracy, weighted_avg
-
-
-
-def create_dict(df, classColumnName):
- return dict(df[classColumnName].value_counts())
-
-def remove_weak_classes(df, classColumnName, threshold):
-
- dictOfClassInstances = create_dict(df,classColumnName)
-
-
- dictionary = {k: v for k, v in dictOfClassInstances.items() if v >= threshold }
- keys = [*dictionary]
- df_tmp = df[~ df[classColumnName].isin(keys)]
- #df = df[df[columnTarget] not in keys]
- #df = df.merge(df_tmp, how = 'outer' ,indicator=True)
- df = pd.concat([df,df_tmp]).drop_duplicates(keep=False)
- return df
-
-
-def split_class(df, columnProcessed):
- i = 0
- new_df = pd.DataFrame(columns= df.columns)
- for index, row in df.iterrows():
- #cls = re.split(';', row[columnProcessed])
- cls = filter(None, row[columnProcessed].split(';'))
- cls = list(cls)
- #cls = re.findall(r"[\w']+", row [columnProcessed])
- r = row
- for categ in cls:
- r[columnProcessed] = categ
- #new_df.append(r, ignore_index = True)
- new_df.loc[i] = r
- i = i + 1
-
- return new_df
-
-
-def resample_classes(df, classColumnName, numberOfInstances):
- # numberOfInstances first elements
- #return df.groupby(classColumnName).apply(lambda x: x[:numberOfInstances][df.columns])
- #random numberOfInstances elements
- replace = False # with replacement
-
- fn = lambda obj: obj.loc[np.random.choice(obj.index, numberOfInstances if len(obj) > numberOfInstances else len(obj), replace),:]
- return df.groupby(classColumnName, as_index=False).apply(fn)
-
-
-def select_classifier(argument):
-
- classifiers = {
-
- 'lr' :LogisticRegression(),
- 'sgd' :SGDClassifier(),
- 'svm' :SVC() ,
- 'decisionTree' :DecisionTreeClassifier(),
- 'rfc' :RandomForestClassifier(),
- 'knn' : KNeighborsClassifier()
- }
-
- param_grid_svm = {'C':[1,10,100,1000],'gamma':[1,0.1,0.001,0.0001], 'kernel':['linear','rbf']}
- param_grid_decisionTree = { 'criterion' : ['gini', 'entropy'], 'max_depth':range(5,10), 'min_samples_split': range(5,10), 'min_samples_leaf': range(1,5) }
- param_grid_rfc = { 'n_estimators': [200, 500], 'max_features': ['auto', 'sqrt', 'log2'], 'max_depth' : [4,5,6,7,8], 'criterion' :['gini', 'entropy'] }
- param_grid_lr = { "penalty":['none',"l2"]}
- param_grid_sgd = { "loss" : ["hinge", "log", "squared_hinge", "modified_huber"], "alpha" : [0.0001, 0.001, 0.01, 0.1], "penalty" : ["l2", "l1", "none"], "max_iter" : [500]}
- param_grid_knn = {'n_neighbors' : list(range(3,20)), 'weights' : ['uniform', 'distance'], 'metric' : ['euclidean', 'manhattan'] }
-
- grid_params = {
-
- 'lr': param_grid_lr,
- 'sgd': param_grid_sgd ,
- 'svm': param_grid_svm,
- 'decisionTree': param_grid_decisionTree,
- 'rfc': param_grid_rfc ,
- 'knn': param_grid_knn,
-
- }
-
- return classifiers.get(argument), grid_params.get(argument)
-
-
-if __name__ == "__main__":
-
-
-
-
-
- print('ok')
- parser = argparse.ArgumentParser()
- parser.add_argument("modelName", help="bert or distilBert or camembert or flaubert")
- parser.add_argument("classifier", help="lr or knn or rfc or decisionTree or sgd or svm")
-
-
- args = parser.parse_args()
- arg = args.modelName
- classifier = args.classifier
-
- config = configparser.ConfigParser()
- config.read('parameters.conf')
-
- minOfInstancePerClass = int(config.get('general','minOfInstancePerClass'))
- maxOfInstancePerClass = int(config.get('general','maxOfInstancePerClass'))
-
- dataPath = config.get('data','dataPath')
- columnText = config.get('data','columnText')
- columnClass = config.get('data','columnClass')
-
-
-
- if not os.path.exists('reports'):
- os.makedirs('reports')
-
- if not os.path.exists(os.path.join('reports', columnClass)):
- os.makedirs(os.path.join('reports', columnClass))
-
-
- dir_name_report = str(minOfInstancePerClass) + '_' + str(maxOfInstancePerClass)
- if not os.path.exists(os.path.join('reports', columnClass, dir_name_report)):
- os.makedirs(os.path.join('reports', columnClass, dir_name_report))
-
-
-
- # read data
- print(dataPath)
- df = pd.read_csv(dataPath)
- df = remove_weak_classes(df, columnClass, minOfInstancePerClass)
- df = resample_classes(df, columnClass, maxOfInstancePerClass)
-
- print(df.head())
- print(df.shape)
- #encode labels
- df = df[df[columnClass] != 'unclassified']
- y = df[columnClass]
- encoder = preprocessing.LabelEncoder()
- y = encoder.fit_transform(y)
-
-
- sentences = df['firstParagraph']
- labels = y.tolist()
-
-
-
- # Features Extraction
- #Bert
- model_class_bert, tokenizer_class_bert, pretrained_weights_bert = (ppb.BertModel, ppb.BertTokenizer, 'bert-base-uncased')
- tokenizer_bert = tokenizer_class_bert.from_pretrained(pretrained_weights_bert)
- model_bert = model_class_bert.from_pretrained(pretrained_weights_bert)
- #DistilBert
- model_class_distilBert, tokenizer_class_distilBert, pretrained_weights_distilBert = (ppb.DistilBertModel, ppb.DistilBertTokenizer, 'distilbert-base-uncased')
- tokenizer_distilBert = tokenizer_class_distilBert.from_pretrained(pretrained_weights_distilBert)
- model_distilBert = model_class_distilBert.from_pretrained(pretrained_weights_distilBert)
- #Camembert
- camembert_tokenizer = CamembertTokenizer.from_pretrained("camembert/camembert-base")
- camembert = CamembertModel.from_pretrained("camembert/camembert-base")
- #Flaubert
-
- flaubert, log = FlaubertModel.from_pretrained('flaubert/flaubert_base_cased', output_loading_info=True)
- flaubert_tokenizer = FlaubertTokenizer.from_pretrained('flaubert/flaubert_base_cased', do_lowercase=False)
-
-
-
- models = {
- 'bert': model_bert,
- 'distilbert': model_distilBert ,
- 'camembert': camembert,
- 'flaubert': flaubert
- }
-
- tokenizers = {
- 'bert': tokenizer_bert,
- 'distilbert': tokenizer_distilBert ,
- 'camembert': camembert_tokenizer,
- 'flaubert': flaubert_tokenizer
-
- }
-
-
-
-
-
-
- if arg == 'flaubert':
- model = flaubert
- tokenizer = flaubert_tokenizer
- elif arg == 'camembert':
- model = camembert
- tokenizer = camembert_tokenizer
-
- elif arg == 'distilbert':
- model = model_distilBert
- tokenizer = tokenizer_distilBert
-
- elif arg == 'bert':
- model = model_bert
- tokenizer = tokenizer_bert
-
-
-
-
-
-
- tokenized = sentences.apply((lambda x: tokenizer.encode(x, add_special_tokens=True, max_length = 512, truncation = True)))
-
- # padding the sequences
- max_len = 0
- for i in tokenized.values:
- if len(i) > max_len:
- max_len = len(i)
-
- padded = np.array([i + [0]*(max_len-len(i)) for i in tokenized.values])
-
-
-
- # attention mask
-
- attention_mask = np.where(padded != 0, 1, 0)
-
-
-
- # get features
- input_ids = torch.tensor(padded)
- attention_mask = torch.tensor(attention_mask)
-
- with torch.no_grad():
- last_hidden_states = model(input_ids, attention_mask=attention_mask)
-
- features = last_hidden_states[0][:,0,:].numpy()
- print(features.shape)
-
- train_x, test_x, train_y, test_y = train_test_split(features, y, test_size=0.33, random_state=42, stratify = y )
-
-
- # classification
-
-
- clf, grid_param = select_classifier(classifier)
-
- print(features)
-
-
-
- clf = GridSearchCV(clf, grid_param, refit = True, verbose = 3)
-
- clf.fit(train_x, train_y)
-
- #evaluation
-
-
- y_pred = clf.predict(test_x)
-
-
- report, accuracy, weighted_avg = evaluate_model(clf, test_x, test_y, y_pred, test_y, [str(e) for e in encoder.transform(encoder.classes_)], encoder.classes_, os.path.join('reports', columnClass, dir_name_report, arg+ '_' + classifier+'.pdf'))
-
- report.to_csv(os.path.join('reports', columnClass, dir_name_report, arg + '_' + classifier +'.csv'))
- with open(os.path.join('reports', columnClass, dir_name_report, arg + '_' + classifier+'.txt'), 'w') as f:
-
- sys.stdout = f # Change the standard output to the file we created.
- print('accuracy : {}'.format(accuracy))
- print('weighted_Precision : {}'.format(weighted_avg['precision']))
- print('weighted_Recall : {}'.format(weighted_avg['recall']))
- print('weighted_F-score : {}'.format(weighted_avg['f1-score']))
- print('weighted_Support : {}'.format(weighted_avg['support']))
- print(dict(zip(encoder.classes_, encoder.transform(encoder.classes_))))
- #sys.stdout = sys.stdout # Reset the standard output to its original value
- sys.stdout = sys.__stdout__
--
GitLab