How to use test_unique_list method in autotest

Best Python code snippet using autotest_python

BERT_CROSS_VALIDATION.py

Source:BERT_CROSS_VALIDATION.py

1from simpletransformers.classification import ClassificationModel2from sklearn.model_selection import StratifiedKFold3from sklearn.metrics import accuracy_score4import pandas as pd5import re6import os 7import matplotlib.pyplot as plt8import seaborn as sns9import numpy as np10from transformers import AutoModel, AutoTokenizer,AutoModelForSequenceClassification,pipeline11from sklearn.metrics import accuracy_score, classification_report, confusion_matrix12def replace_with_index(x):13    index = unique_list.index(x)14    return index15def cleanText(input_sentence):16  17    tmp= [word.replace('A','a') for word in input_sentence.split(' ')]18    tmp= [word.lower() for word in tmp]19    tmp= [word.replace('iÌ','i') for word in tmp]20    tmp = [re.sub('[^A-Za-z0-9ÄÃ¼ÅÄ±Ã§Ã¶iÃ¢Ã®]+', ' ', word) for word in tmp]21    tmp = [word.strip(' ') for word in tmp]22    tmp1 =' '.join(tmp)23    return tmp124def get_model(path,X_test,y_test):25    result = {}26    plt.rcParams["figure.figsize"] = (50,30)27    for epoch in path:28      tokenizer= AutoTokenizer.from_pretrained(path)29      # build and load model, it take time depending on your internet connection30      model= AutoModelForSequenceClassification.from_pretrained(path)31      # make pipeline32      nlp=pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)33      34      test = pd.concat([X_test,y_test],axis=1)35      #print(test)36      test_unique_list = test['label'].unique().tolist()37      test_unique_list.sort()38      #print(test_unique_list)39      pred_label_list, true_label_list = [],[]40      cou = 041      for t,l in zip(test["metin"], test["label"]):42        cou+=143        true_label_list.append(l)44        pred_label_list.append(int(nlp(t)[0]["label"].lstrip("LABEL_")))45        if cou %1000 == 0:46          print(path.index(epoch),cou)47      df = pd.DataFrame()48      df["true"] = true_label_list49      df["pred"] = pred_label_list50      print(df)51      for item in test_unique_list:52        true_df = df[df.true == item]53        class_acc = accuracy_score(true_df["true"], true_df["pred"])54        print('ID = {} ACC = {}'.format(item, class_acc),file=open("output.txt", "a"))55      56      acc = accuracy_score(df["true"], df["pred"])57      result[f"{path.index(epoch)+1}. epoch Accuracy"] = acc58      print('acc = {}'.format(acc),file=open("output.txt", "a"))59      print(classification_report(df["true"], df["pred"]),file=open("output.txt", "a"))60      """sns.heatmap(confusion_matrix(df["true"], df["pred"]), annot = True, fmt = "g")61      plt.show()"""62      return df63HUGGINGFACE_MODEL_PATH = "loodos/bert-base-turkish-uncased"64tokenizer = AutoTokenizer.from_pretrained(HUGGINGFACE_MODEL_PATH)65print('Zero_ShotsÄ±z_ve_Zero_ShotlÄ±_BERT_Result',file=open("output.txt", "a"))66list_url = [['Single_BERT_DATASET_PATH','No_ZEROSHOT'],['FÄ°LTERED_BY_ZEROSHOT_RESULT_DATASET_PATH','W_ZEROSHOT']]67    68for item in list_url:69  print(item[1],file=open("output.txt", "a"))70  data = pd.read_csv(item[0])71  unique_list = data['label'].unique().tolist()72  data['label'] = data['label'].apply(lambda x: replace_with_index(x))73  data = data.iloc[:,:2]74  for i in range(len(data['label'])):75    if isinstance(data['label'][i], np.generic):76      data['label'][i]= np.asscalar(data['label'][i])77  data.dropna(axis= 0, inplace=True)78  data = data.reset_index(drop = True)79  data["metin"] = data["metin"].apply(cleanText)80  print(len(data))81  data = data.drop_duplicates()82  print(len(data))83  data=data.sample(frac=1)84  data = data.reset_index(drop= True)85  # prepare cross validation86  n=587  kf = StratifiedKFold(n_splits=n, random_state=42, shuffle=True)88  no_labels = len(set(data["label"]))89  results = []90  for i,(train_index, val_index) in enumerate(kf.split(data["metin"],data["label"])):91      print('Kesit No: {}'.format(i),file=open("output.txt", "a"))92      # splitting Dataframe (dataset not included)93      X_train, X_test = data["metin"][train_index], data["metin"][val_index]94      y_train, y_test = data["label"][train_index], data["label"][val_index]95      96      train_df = pd.concat([X_train,y_train], axis = 1)97      val_df = pd.concat([X_test,y_test], axis = 1)98      # Defining Model99      MODEL_OUTPUT_DIR = 'BERT_{}_44_kategori_{}/'.format(item[1],i,)100      #model = AutoModel.from_pretrained(HUGGINGFACE_MODEL_PATH)101      model_args = {102          "use_early_stopping": True,103          "early_stopping_delta": 0.01,104          "early_stopping_metric": "mcc",105          "early_stopping_metric_minimize": False,106          "early_stopping_patience": 5,107          "evaluate_during_training_steps": 6000,108          "fp16": False,109          "num_train_epochs":3110          #"overwrite_output_dir": True111      }112      model = ClassificationModel(113          "bert", 114          HUGGINGFACE_MODEL_PATH,115          use_cuda=True, 116          args=model_args, 117          num_labels=no_labels118      )119      model.train_model(train_df, acc=accuracy_score, output_dir=MODEL_OUTPUT_DIR)120      EPOCH_PATH = [MODEL_OUTPUT_DIR +"/"+ t for t in os.listdir(MODEL_OUTPUT_DIR) if "epoch" in t and "-3"in t]121      EPOCH_PATH=EPOCH_PATH[0]122      data_test = pd.DataFrame()...

Single_BERT.py

Source:Single_BERT.py

1from sklearn.model_selection import train_test_split2import sklearn3import os4from sklearn.metrics import accuracy_score, classification_report, confusion_matrix5import pandas as pd6import numpy as np7import matplotlib.pyplot as plt8import seaborn as sns9from transformers import AutoModel, AutoTokenizer,AutoModelForSequenceClassification,pipeline10import re11from simpletransformers.classification import ClassificationModel12data = pd.read_csv('data set path according to which method you will use ')13HUGGINGFACE_MODEL_PATH = "loodos/bert-base-turkish-uncased"14MODEL_OUTPUT_DIR = 'BERT4_no_zero_shot_44/'15#data = data[data.groupby('kategori')['kategori'].transform('size') > 200]16#data = data.reset_index(drop = True)17unique_list = data['label'].unique().tolist()18def replace_with_index(x):19  index = unique_list.index(x)20  return index21data['label'] = data['label'].apply(lambda x: replace_with_index(x))22data = data.iloc[:,:2]23for i in range(len(data['label'])):24  if isinstance(data['label'][i], np.generic):25    data['label'][i]= np.asscalar(data['label'][i])26data.dropna(axis= 0, inplace=True)27data = data.reset_index(drop = True)28def cleanText(input_sentence):29 30  tmp= [word.replace('A','a') for word in input_sentence.split(' ')]31  tmp= [word.lower() for word in tmp]32  tmp= [word.replace('iÌ','i') for word in tmp]33  tmp = [re.sub('[^A-Za-z0-9ÄÃ¼ÅÄ±Ã§Ã¶iÃ¢Ã®]+', ' ', word) for word in tmp]34  tmp = [word.strip(' ') for word in tmp]35  tmp1 =' '.join(tmp)36  return tmp137data["metin"] = data["metin"].apply(cleanText)38print(len(data))39data = data.drop_duplicates()40print(len(data))41data=data.sample(frac=1)42data = data.reset_index(drop= True)43#print(data['label'].unique())44X_train, X_test, y_train, y_test = train_test_split(data["metin"],data["label"], test_size= .2, stratify=data['label'], random_state = 42)45train = pd.concat([X_train,y_train], axis = 1)46tokenizer = AutoTokenizer.from_pretrained(HUGGINGFACE_MODEL_PATH)47model = AutoModel.from_pretrained(HUGGINGFACE_MODEL_PATH)48no_labels = len(set(data["label"]))49model_args = {50    "use_early_stopping": True,51    "early_stopping_delta": 0.01,52    "early_stopping_metric": "mcc",53    "early_stopping_metric_minimize": False,54    "early_stopping_patience": 5,55    "evaluate_during_training_steps": 6000,56    "fp16": False,57    "num_train_epochs":358}59model = ClassificationModel(60    "bert", 61    HUGGINGFACE_MODEL_PATH,62     use_cuda=True, 63     args=model_args, 64     num_labels=no_labels65)66model.train_model(train, acc=sklearn.metrics.accuracy_score, output_dir=MODEL_OUTPUT_DIR)67EPOCH_PATH = [MODEL_OUTPUT_DIR +"/"+ i for i in os.listdir(MODEL_OUTPUT_DIR) if "epoch" in i and "-3"in i]68EPOCH_PATH=EPOCH_PATH[0]69def get_model(path):70  result = {}71  plt.rcParams["figure.figsize"] = (50,30)72  for epoch in path:73    tokenizer= AutoTokenizer.from_pretrained(EPOCH_PATH)74    # build and load model, it take time depending on your internet connection75    model= AutoModelForSequenceClassification.from_pretrained(EPOCH_PATH)76    # make pipeline77    nlp=pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)78    79    test = pd.concat([X_test,y_test],axis=1)80    print(test)81    #test_unique_list = test['label'].unique().tolist()82    #test_unique_list.sort()83    #print(test_unique_list)84    pred_label_list, true_label_list = [],[]85    cou = 086    for t,l in zip(test["metin"], test["label"]):87      cou+=188      true_label_list.append(l)89      pred_label_list.append(int(nlp(t)[0]["label"].lstrip("LABEL_")))90      if cou %1000 == 0:91        print(EPOCH_PATH.index(epoch),cou)92    df = pd.DataFrame()93    df["true"] = true_label_list94    df["pred"] = pred_label_list95    print(df)96    """for item in test_unique_list:97      true_df = df[df.true == item]98      class_acc = accuracy_score(true_df["true"], true_df["pred"])99      print('ID = {} ACC = {}'.format(item, class_acc))"""100    101    acc = accuracy_score(df["true"], df["pred"])102    result[f"{EPOCH_PATH.index(epoch)+1}. epoch Accuracy"] = acc103    print(acc)104    print(classification_report(df["true"], df["pred"]))105    sns.heatmap(confusion_matrix(df["true"], df["pred"]), annot = True, fmt = "g")106    plt.show()107    return df108data_test = pd.DataFrame()...

utils.py

Source:utils.py

1import unittest2import numpy as np3from radbm.utils import unique_list, Ramp4class Test_unique_list(unittest.TestCase):5    def test_unique_list(self):6        it = [3,4,4,2,1,1,0,3,2]7        expected_list = [3,4,2,1,0]8        result = unique_list(it)9        self.assertEqual(result, expected_list)10        11class TestRamp(unittest.TestCase):12    def test_ramp(self):13        #from x=3..5 we ramp from y=-1..714        ramp = Ramp(3, 5, -1, 7)15        xs = np.array([2, 3, 4, 5, 6])16        ys = np.array([-1, -1, 3, 7, 7])...

Automation Testing Tutorials

Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.