Removed nullcontext for python 3.6 compatibility

README.md

@@ -1644,6 +1644,14 @@ Note, you must set `evaluate_generated_text` to `True` to evaluate generated seq
 import logging
 
 import pandas as pd
+import sklearn
+
+from simpletransformers.classification import ClassificationModel
+from simpletransformers.classification.multi_modal_classification_model import \
+    MultiModalClassificationModel
+from simpletransformers.experimental.classification import ClassificationModel
+from simpletransformers.language_representation import RepresentationModel
+from simpletransformers.seq2seq import Seq2SeqModel
 from simpletransformers.t5 import T5Model
 
 logging.basicConfig(level=logging.INFO)
@@ -1952,10 +1960,7 @@ The prediction data should be a list of strings.
 The `Seq2SeqModel` must be initialized with `encoder_decoder_type="bart"` and `encoder_decoder_name` set to a pre-trained model name or the path to a saved model directory.
 
 ```python
-import logging
 
-import pandas as pd
-from simpletransformers.seq2seq import Seq2SeqModel
 
 logging.basicConfig(level=logging.INFO)
 transformers_logger = logging.getLogger("transformers")
@@ -2025,10 +2030,7 @@ The `Seq2SeqModel` must be initialized with `encoder_decoder_type="marian"` and
 Everything else is identical to the Bart model usage.
 
 ```python
-import logging
 
-import pandas as pd
-from simpletransformers.seq2seq import Seq2SeqModel
 
 logging.basicConfig(level=logging.INFO)
 transformers_logger = logging.getLogger("transformers")
@@ -2074,10 +2076,7 @@ for en, de in zip(src, predictions):
 #### Generic Encoder-Decoder minimal start
 
 ```python
-import logging
 
-import pandas as pd
-from simpletransformers.seq2seq import Seq2SeqModel
 
 logging.basicConfig(level=logging.INFO)
 transformers_logger = logging.getLogger("transformers")
@@ -2794,7 +2793,6 @@ If `label_list` is not given, `num_labels` is required and the labels should be
 Create a `MultiModalClassificationModel`.
 
 ```python
-from simpletransformers.classification.multi_modal_classification_model import MultiModalClassificationModel
 
 
 model = MultiModalClassificationModel("bert", "bert-base-uncased")
@@ -2929,7 +2927,6 @@ For more complete examples of how to use this component with downstream tasks re
 ### Minimal example for generating word embeddings
 Generate a list of contextual word embeddings for every sentence in a list
 ```python
-from simpletransformers.language_representation import RepresentationModel
 
 sentences = ["Example sentence 1", "Example sentence 2"]
 model = RepresentationModel(
@@ -2944,7 +2941,6 @@ assert word_vectors.shape === (2, 5, 768) # token vector for every token in each
 ### Minimal example for generating sentence embeddings 
 Same code as for generating word embeddings, the only differennce is that we pass combine_s`trategy="mean" parameter to `combine_strategy="mean"
 ```python
-from simpletransformers.language_representation import RepresentationModel
 sentences = ["Example sentence 1", "Example sentence 2"]
 model = RepresentationModel(
         model_type="bert",
@@ -2973,8 +2969,6 @@ Regression can be used with either single sentence or sentence pair tasks.
 #### Minimal Start for Regression
 
 ```python
-from simpletransformers.classification import ClassificationModel
-import pandas as pd
 
 
 train_data = [
@@ -3039,7 +3033,6 @@ _[Back to Table of Contents](#table-of-contents)_
 To use experimental features, import from `simpletransformers.experimental.X`
 
 ```python
-from simpletransformers.experimental.classification import ClassificationModel
 ```
 
 ### Sliding Window For Long Sequences
@@ -3060,9 +3053,6 @@ Currently available on binary and multiclass classification models of the follow
 Set `sliding_window` to `True` for the ClassificationModel to enable this feature.
 
 ```python
-from simpletransformers.classification import ClassificationModel
-import pandas as pd
-import sklearn
 
 # Train and Evaluation data needs to be in a Pandas Dataframe of two columns. The first column is the text with type str, and the second column in the label with type int.
 train_data = [['Example sentence belonging to class 1' * 50, 1], ['Example sentence belonging to class 0', 0], ['Example  2 sentence belonging to class 0', 0]] + [['Example sentence belonging to class 0', 0] for i in range(12)]

examples/hyperparameter tuning/extended-tuning/data_prep.py

@@ -2,7 +2,6 @@
 
 from utils import load_rte_data_file
 
-
 # Preparing train data
 train_df = load_rte_data_file("data/train.jsonl")
 eval_df = load_rte_data_file("data/val.jsonl")

examples/hyperparameter tuning/extended-tuning/sweep_layerwise.py

@@ -2,9 +2,9 @@
 from statistics import mean
 
 import pandas as pd
+import wandb
 from sklearn.metrics import accuracy_score
 
-import wandb
 from simpletransformers.classification import ClassificationArgs, ClassificationModel
 from utils import load_rte_data_file
 

examples/hyperparameter tuning/extended-tuning/sweep_vanilla.py

@@ -2,10 +2,10 @@
 from statistics import mean, mode
 
 import pandas as pd
+import wandb
 from sklearn.metrics import accuracy_score, f1_score
 from sklearn.model_selection import train_test_split
 
-import wandb
 from simpletransformers.classification import ClassificationArgs, ClassificationModel
 from utils import load_rte_data_file
 

examples/hyperparameter tuning/extended-tuning/train_default.py

@@ -2,13 +2,12 @@
 from statistics import mean
 
 import pandas as pd
+import wandb
 from sklearn.metrics import accuracy_score
 
-import wandb
 from simpletransformers.classification import ClassificationArgs, ClassificationModel
 from utils import load_rte_data_file
 
-
 logging.basicConfig(level=logging.INFO)
 transformers_logger = logging.getLogger("transformers")
 transformers_logger.setLevel(logging.WARNING)

examples/hyperparameter tuning/extended-tuning/train_layerwise.py

@@ -3,10 +3,10 @@
 
 import pandas as pd
 import prettyprinter
+import wandb
 from prettyprinter import pprint
 from sklearn.metrics import accuracy_score
 
-import wandb
 from simpletransformers.classification import ClassificationArgs, ClassificationModel
 from utils import load_rte_data_file
 

examples/hyperparameter tuning/extended-tuning/train_vanilla.py

@@ -3,10 +3,10 @@
 
 import pandas as pd
 import prettyprinter
+import wandb
 from prettyprinter import pprint
 from sklearn.metrics import accuracy_score, f1_score
 
-import wandb
 from simpletransformers.classification import ClassificationArgs, ClassificationModel
 from utils import load_rte_data_file
 

examples/hyperparameter tuning/sweeps.py

@@ -2,12 +2,9 @@
 
 import pandas as pd
 import sklearn
-
 import wandb
-from simpletransformers.classification import (
-    ClassificationArgs,
-    ClassificationModel,
-)
+
+from simpletransformers.classification import ClassificationArgs, ClassificationModel
 
 sweep_config = {
     "method": "bayes",  # grid, random

examples/language_generation/data_prep.py

@@ -1,6 +1,5 @@
 import pandas as pd
 
-
 df = pd.read_csv("data/cs.AI.tsv", sep="\t")
 abstracts = df["abstract"].tolist()
 

examples/language_generation/fine_tune.py

@@ -1,6 +1,6 @@
-from simpletransformers.language_modeling import LanguageModelingModel
 import logging
 
+from simpletransformers.language_modeling import LanguageModelingModel
 
 logging.basicConfig(level=logging.INFO)
 transformers_logger = logging.getLogger("transformers")

examples/language_generation/generate.py

@@ -1,6 +1,6 @@
 import logging
-from simpletransformers.language_generation import LanguageGenerationModel
 
+from simpletransformers.language_generation import LanguageGenerationModel
 
 logging.basicConfig(level=logging.INFO)
 transformers_logger = logging.getLogger("transformers")

examples/language_generation/train_new_lm.py

@@ -1,7 +1,7 @@
-from simpletransformers.language_modeling import LanguageModelingModel
-import logging
 import argparse
+import logging
 
+from simpletransformers.language_modeling import LanguageModelingModel
 
 logging.basicConfig(level=logging.INFO)
 transformers_logger = logging.getLogger("transformers")

examples/language_representation/binary_classification_dummy.py

@@ -1,6 +1,7 @@
 import pandas as pd
-from sklearn.metrics import classification_report
 from sklearn.linear_model import RidgeClassifier
+from sklearn.metrics import classification_report
+
 from simpletransformers.language_representation import RepresentationModel
 
 train_data = [["Example sentence belonging to class 1", 1], ["Example sentence belonging to class 0", 0]]

examples/language_representation/classification_yelp_polarity/classification_yelp.py

@@ -1,8 +1,10 @@
+from os.path import dirname, join
+
 import pandas as pd
-from sklearn.metrics import classification_report
 from sklearn.linear_model import RidgeClassifier
+from sklearn.metrics import classification_report
+
 from simpletransformers.language_representation import RepresentationModel
-from os.path import dirname, join
 
 project_root = dirname(dirname(dirname(dirname(__file__))))  # path to root of the project
 

examples/named_entity_recognition/named_entity_recognition.py

@@ -1,8 +1,9 @@
-import pandas as pd
-from simpletransformers.ner import NERModel
 import numpy as np
+import pandas as pd
 from scipy.special import softmax
 
+from simpletransformers.ner import NERModel
+
 # Creating train_df  and eval_df for demonstration
 train_data = [
     [0, "Simple", "B-MISC"],

examples/seq2seq/minimal_seq2seq.py

@@ -1,6 +1,7 @@
 import logging
 
 import pandas as pd
+
 from simpletransformers.seq2seq import Seq2SeqModel
 
 logging.basicConfig(level=logging.INFO)

examples/t5/mixed_tasks/test.py

@@ -6,10 +6,11 @@
 import numpy as np
 import pandas as pd
 from scipy.stats import pearsonr, spearmanr
-from simpletransformers.t5 import T5Model
 from sklearn.metrics import accuracy_score, f1_score
 from transformers.data.metrics.squad_metrics import compute_exact, compute_f1
 
+from simpletransformers.t5 import T5Model
+
 
 def f1(truths, preds):
     return mean([compute_f1(truth, pred) for truth, pred in zip(truths, preds)])

examples/t5/mixed_tasks/train.py

@@ -1,6 +1,6 @@
 import pandas as pd
-from simpletransformers.t5 import T5Model
 
+from simpletransformers.t5 import T5Model
 
 train_df = pd.read_csv("data/train.tsv", sep="\t").astype(str)
 eval_df = pd.read_csv("data/eval.tsv", sep="\t").astype(str)

examples/t5/training_on_a_new_task/data_prep.py

@@ -1,7 +1,8 @@
-import pandas as pd
 import gzip
-from sklearn.model_selection import train_test_split
 import os
+
+import pandas as pd
+from sklearn.model_selection import train_test_split
 from tqdm.auto import tqdm
 
 

examples/t5/training_on_a_new_task/predict.py

@@ -1,6 +1,5 @@
 from simpletransformers.t5 import T5Model
 
-
 model_args = {
     "reprocess_input_data": True,
     "overwrite_output_dir": True,

examples/t5/training_on_a_new_task/test.py

@@ -1,7 +1,8 @@
-from simpletransformers.t5 import T5Model
-import pandas as pd
 from pprint import pprint
 
+import pandas as pd
+
+from simpletransformers.t5 import T5Model
 
 model_args = {
     "reprocess_input_data": True,

examples/t5/training_on_a_new_task/train.py

@@ -2,7 +2,6 @@
 
 from simpletransformers.t5 import T5Model
 
-
 train_df = pd.read_csv("data/train_df.tsv", sep="\t").astype(str)
 eval_df = pd.read_csv("data/eval_df.tsv", sep="\t").astype(str)
 

examples/text_classification/binary_classification.py

@@ -1,4 +1,5 @@
 import pandas as pd
+
 from simpletransformers.classification import ClassificationModel
 
 # Train and Evaluation data needs to be in a Pandas Dataframe of two columns. The first column is the text with type str, and the second column is the label with type int.

examples/text_classification/lazy_loading_regression.py

@@ -1,8 +1,8 @@
 import os
 
 import pandas as pd
-from simpletransformers.classification import ClassificationModel
 
+from simpletransformers.classification import ClassificationModel
 
 train_data = [
     ["Example sentence belonging to class 1", "Yep, this is 1", 0.8],

examples/text_classification/multiclass_classification.py

@@ -1,4 +1,5 @@
 import pandas as pd
+
 from simpletransformers.classification import ClassificationModel
 
 # Train and Evaluation data needs to be in a Pandas Dataframe containing at least two columns. If the Dataframe has a header, it should contain a 'text' and a 'labels' column. If no header is present, the Dataframe should contain at least two columns, with the first column is the text with type str, and the second column in the label with type int.

examples/text_classification/multilabel_classification.py

@@ -1,4 +1,5 @@
 import pandas as pd
+
 from simpletransformers.classification import MultiLabelClassificationModel
 
 # Train and Evaluation data needs to be in a Pandas Dataframe containing at least two columns, a 'text' and a 'labels' column. The `labels` column should contain multi-hot encoded lists.

examples/text_classification/yelp_reviews_polarity/train.py

@@ -1,8 +1,8 @@
 import sys
 
 import pandas as pd
-from simpletransformers.classification import ClassificationModel
 
+from simpletransformers.classification import ClassificationModel
 
 prefix = "data/"
 

requirements-dev.txt

@@ -6,4 +6,4 @@ pytest==5.1.3
 # lint/format/types
 black==19.10b0
 flake8==3.7.8
-pytype==2019.7.11
+pytype==2019.7.11

setup.py

@@ -5,7 +5,7 @@
 
 setup(
     name="simpletransformers",
-    version="0.46.5",
+    version="0.46.6",
     author="Thilina Rajapakse",
     author_email="[email protected]",
     description="An easy-to-use wrapper library for the Transformers library.",

simpletransformers/classification/__init__.py

@@ -1,6 +1,8 @@
 from simpletransformers.classification.classification_model import ClassificationModel
 from simpletransformers.classification.multi_label_classification_model import MultiLabelClassificationModel
 from simpletransformers.classification.multi_modal_classification_model import MultiModalClassificationModel
-from simpletransformers.config.model_args import ClassificationArgs
-from simpletransformers.config.model_args import MultiLabelClassificationArgs
-from simpletransformers.config.model_args import MultiModalClassificationArgs
+from simpletransformers.config.model_args import (
+    ClassificationArgs,
+    MultiLabelClassificationArgs,
+    MultiModalClassificationArgs,
+)