Remove unused imports

examples/ag_news.py

@@ -1,6 +1,5 @@
 import numpy as np
 from sklearn.metrics import classification_report
-from sklearn.utils import shuffle
 from torchtext.datasets import AG_NEWS
 
 from npc_gzip.compressors.base import BaseCompressor

examples/imdb.py

@@ -1,6 +1,5 @@
 import numpy as np
 from sklearn.metrics import classification_report
-from sklearn.utils import shuffle
 from torchtext.datasets import IMDB
 
 from npc_gzip.compressors.base import BaseCompressor

npc_gzip/aggregations.py

@@ -1,7 +1,5 @@
 import itertools
 
-import numpy as np
-
 
 def concatenate_with_space(stringa: str, stringb: str) -> str:
     """

npc_gzip/distance.py

@@ -1,4 +1,4 @@
-from typing import Sequence, Union
+from typing import Sequence
 
 import numpy as np
 

npc_gzip/knn_classifier.py

@@ -1,4 +1,4 @@
-from typing import Optional, Sequence, Union
+from typing import Optional, Sequence
 
 import numpy as np
 from tqdm import tqdm
@@ -86,10 +86,10 @@ def __init__(
         assert (
             self.training_inputs.shape == self.training_labels.shape
         ), f"""
-        Training Inputs and Labels did not maintain their 
+        Training Inputs and Labels did not maintain their
         shape during the conversion from lists to numpy arrays.
         This is most likely a bug in the numpy package:
-        
+
         self.training_inputs.shape: {self.training_inputs.shape}
         self.training_labels.shape: {self.training_labels.shape}
         """
@@ -309,9 +309,9 @@ def predict(
         assert (
             top_k <= x.shape[0]
         ), f"""
-        top_k ({top_k}) must be less or equal to than the number of 
+        top_k ({top_k}) must be less or equal to than the number of
         samples provided to be predicted on ({x.shape[0]})
-        
+
         """
 
         # sample training inputs and labels

npc_gzip/utils.py

@@ -10,14 +10,12 @@
 import random
 import string
 
-from npc_gzip.exceptions import InvalidObjectTypeException
-
 
 def generate_sentence(number_of_words: int = 10) -> str:
     """
     Generates a sentence of random
-    numbers and letters, with 
-    `number_of_words` words in the 
+    numbers and letters, with
+    `number_of_words` words in the
     sentence such that len(out.split()) \
     == `number_of_words`.
 

original_codebase/data.py

@@ -1,16 +1,14 @@
 import csv
 import os
 import random
-from collections import OrderedDict, defaultdict
+from collections import defaultdict
 from collections.abc import Iterable
 from typing import Optional, Sequence, Union
 
 import numpy as np
-import torch
 import unidecode
 from datasets import load_dataset
 from sklearn.datasets import fetch_20newsgroups
-from torch.utils.data import DataLoader, Subset
 
 
 def _load_csv_filepath(csv_filepath: str) -> list:

original_codebase/experiments.py

@@ -1,20 +1,11 @@
 # Experiment framework
 import operator
-import os
-import pickle
 import random
-import statistics
-from collections import Counter, defaultdict
-from copy import deepcopy
-from functools import partial
-from itertools import repeat
-from statistics import mode
+from collections import defaultdict
 from typing import Any, Callable, Optional
 
 import numpy as np
-import torch
 from compressors import DefaultCompressor
-from sklearn.metrics.cluster import adjusted_rand_score, normalized_mutual_info_score
 from tqdm import tqdm
 
 

tests/test_aggregations.py

@@ -1,7 +1,4 @@
-import pytest
-
 from npc_gzip.aggregations import aggregate_strings, concatenate_with_space
-from npc_gzip.exceptions import StringTooShortException
 
 
 class TestAggregations:

tests/test_base_compressor.py

@@ -1,5 +1,4 @@
 import gzip
-from types import ModuleType
 
 import pytest
 

tests/test_bz2_compressor.py

@@ -1,11 +1,7 @@
 import bz2
-from types import ModuleType
-
-import pytest
 
 from npc_gzip.compressors.base import BaseCompressor
 from npc_gzip.compressors.bz2_compressor import Bz2Compressor
-from npc_gzip.exceptions import InvalidCompressorException
 
 
 class TestBz2Compressor:

tests/test_gzip_compressor.py

@@ -1,11 +1,7 @@
 import gzip
-from types import ModuleType
-
-import pytest
 
 from npc_gzip.compressors.base import BaseCompressor
 from npc_gzip.compressors.gzip_compressor import GZipCompressor
-from npc_gzip.exceptions import InvalidCompressorException
 
 
 class TestBz2Compressor:

tests/test_knn_classifier.py

@@ -7,10 +7,8 @@
 from npc_gzip.compressors.bz2_compressor import Bz2Compressor
 from npc_gzip.compressors.gzip_compressor import GZipCompressor
 from npc_gzip.compressors.lzma_compressor import LzmaCompressor
-from npc_gzip.distance import Distance
 from npc_gzip.exceptions import (
     InputLabelEqualLengthException,
-    InvalidObjectTypeException,
     UnsupportedDistanceMetricException,
 )
 from npc_gzip.knn_classifier import KnnClassifier

tests/test_lzma_compressor.py

@@ -1,11 +1,7 @@
 import lzma
-from types import ModuleType
-
-import pytest
 
 from npc_gzip.compressors.base import BaseCompressor
 from npc_gzip.compressors.lzma_compressor import LzmaCompressor
-from npc_gzip.exceptions import InvalidCompressorException
 
 
 class TestBz2Compressor:

tests/test_utils.py

@@ -2,7 +2,6 @@
 
 import pytest
 
-from npc_gzip.exceptions import InvalidObjectTypeException
 from npc_gzip.utils import generate_dataset, generate_sentence