The distribution of size of files (measured in lines of code).
File | # lines | # units |
---|---|---|
code_tokenizer.py in preprocessing/src |
691 | 28 |
trainer.py in XLM/src |
681 | 29 |
utils.py in XLM/src |
555 | 27 |
transformer.py in XLM/src/model |
478 | 22 |
javalang_tokenizer.py in preprocessing/src |
455 | 31 |
evaluator.py in XLM/src/evaluation |
447 | 13 |
dataset.py in XLM/src/data |
284 | 22 |
loader.py in XLM/src/data |
246 | 7 |
train.py in XLM |
235 | 2 |
dataset.py in preprocessing/src |
228 | 13 |
utils.py in preprocessing/src |
203 | 21 |
optim.py in XLM/src |
184 | 10 |
__init__.py in XLM/src/model |
177 | 3 |
dictionary.py in XLM/src/data |
167 | 11 |
SORT_ARRAY_APPLYING_GIVEN_EQUATION.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
157 | 2 |
translate.py in root |
124 | 3 |
FIND_THREE_ELEMENT_FROM_DIFFERENT_THREE_ARRAYS_SUCH_THAT_THAT_A_B_C_K_1.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
115 | 2 |
FIND_MAXIMUM_SUM_POSSIBLE_EQUAL_SUM_THREE_STACKS.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
104 | 2 |
FIND_THREE_ELEMENT_FROM_DIFFERENT_THREE_ARRAYS_SUCH_THAT_THAT_A_B_C_K.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
104 | 2 |
STOOGE_SORT.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
99 | 2 |
slurm.py in XLM/src |
98 | 4 |
SORT_EVEN_PLACED_ELEMENTS_INCREASING_ODD_PLACED_DECREASING_ORDER.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
96 | 2 |
SPLIT_ARRAY_ADD_FIRST_PART_END.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
96 | 2 |
HIGHWAY_BILLBOARD_PROBLEM.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
93 | 2 |
SCHEDULE_JOBS_SERVER_GETS_EQUAL_LOAD.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
92 | 2 |
FUNCTION_COPY_STRING_ITERATIVE_RECURSIVE_1.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
92 | 2 |
DYNAMIC_PROGRAMMING_SET_37_BOOLEAN_PARENTHESIZATION_PROBLEM.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
90 | 2 |
CHECK_TWO_GIVEN_CIRCLES_TOUCH_INTERSECT.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
90 | 2 |
preprocess.py in preprocessing |
89 | 2 |
FIND_DISTINCT_SUBSET_SUBSEQUENCE_SUMS_ARRAY.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
89 | 2 |
CHANGE_ARRAY_PERMUTATION_NUMBERS_1_N.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
87 | 2 |
MINIMUM_COST_CUT_BOARD_SQUARES.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
87 | 2 |
DYNAMIC_PROGRAMMING_SET_37_BOOLEAN_PARENTHESIZATION_PROBLEM.cpp in data/evaluation/geeks_for_geeks_successful_test_scripts/cpp |
87 | 2 |
COUNT_PAIRS_TWO_SORTED_ARRAYS_WHOSE_SUM_EQUAL_GIVEN_VALUE_X_2.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
86 | 2 |
FIND_THE_MINIMUM_DISTANCE_BETWEEN_TWO_NUMBERS_1.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
86 | 2 |
K_TH_MISSING_ELEMENT_INCREASING_SEQUENCE_NOT_PRESENT_GIVEN_SEQUENCE.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
86 | 2 |
REARRANGE_POSITIVE_AND_NEGATIVE_NUMBERS_PUBLISH.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
84 | 2 |
COUNT_PAIRS_TWO_SORTED_ARRAYS_WHOSE_SUM_EQUAL_GIVEN_VALUE_X_1.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
83 | 2 |
K_TH_ELEMENT_TWO_SORTED_ARRAYS.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
83 | 2 |
MINIMUM_COST_TO_FILL_GIVEN_WEIGHT_IN_A_BAG.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
83 | 2 |
LONGEST_COMMON_INCREASING_SUBSEQUENCE_LCS_LIS.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
83 | 2 |
REARRANGE_ARRAY_MAXIMUM_MINIMUM_FORM_SET_2_O1_EXTRA_SPACE.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
82 | 2 |
STACK_PERMUTATIONS_CHECK_IF_AN_ARRAY_IS_STACK_PERMUTATION_OF_OTHER.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
82 | 2 |
MAKE_LARGEST_PALINDROME_CHANGING_K_DIGITS.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
81 | 2 |
COUNT_PAIRS_TWO_SORTED_ARRAYS_WHOSE_SUM_EQUAL_GIVEN_VALUE_X.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
81 | 2 |
MEDIAN_OF_TWO_SORTED_ARRAYS.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
81 | 2 |
REMOVE_MINIMUM_NUMBER_ELEMENTS_NO_COMMON_ELEMENT_EXIST_ARRAY.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
81 | 2 |
PRODUCT_MAXIMUM_FIRST_ARRAY_MINIMUM_SECOND_1.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
81 | 2 |
embedder.py in XLM/src/model |
80 | 7 |
LONGEST_COMMON_SUBSTRING.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
80 | 2 |
File | # lines | # units |
---|---|---|
javalang_tokenizer.py in preprocessing/src |
455 | 31 |
trainer.py in XLM/src |
681 | 29 |
code_tokenizer.py in preprocessing/src |
691 | 28 |
utils.py in XLM/src |
555 | 27 |
transformer.py in XLM/src/model |
478 | 22 |
dataset.py in XLM/src/data |
284 | 22 |
utils.py in preprocessing/src |
203 | 21 |
evaluator.py in XLM/src/evaluation |
447 | 13 |
dataset.py in preprocessing/src |
228 | 13 |
dictionary.py in XLM/src/data |
167 | 11 |
optim.py in XLM/src |
184 | 10 |
embedder.py in XLM/src/model |
80 | 7 |
loader.py in XLM/src/data |
246 | 7 |
slurm.py in XLM/src |
98 | 4 |
pretrain.py in XLM/src/model |
59 | 4 |
translate.py in root |
124 | 3 |
logger.py in XLM/src |
38 | 3 |
__init__.py in XLM/src/model |
177 | 3 |
train.py in XLM |
235 | 2 |
preprocess.py in preprocessing |
89 | 2 |
There are 982 files with lines longer than 120 characters. In total, there are 3030 long lines.
File | # lines | # units | # long lines |
---|---|---|---|
FUNCTION_COPY_STRING_ITERATIVE_RECURSIVE_1.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
92 | 2 | 19 |
LEXICOGRAPHICALLY_LARGEST_SUBSEQUENCE_EVERY_CHARACTER_OCCURS_LEAST_K_TIMES.py in data/evaluation/geeks_for_geeks_successful_test_scripts/python |
50 | 1 | 18 |
SWAP_TWO_NUMBERS_WITHOUT_USING_TEMPORARY_VARIABLE.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
68 | 2 | 17 |
PROGRAM_WORST_FIT_ALGORITHM_MEMORY_MANAGEMENT.py in data/evaluation/geeks_for_geeks_successful_test_scripts/python |
52 | 1 | 16 |
SWAP_TWO_NUMBERS_WITHOUT_USING_TEMPORARY_VARIABLE.py in data/evaluation/geeks_for_geeks_successful_test_scripts/python |
36 | 1 | 16 |
REPLACE_OCCURRENCES_STRING_AB_C_WITHOUT_USING_EXTRA_SPACE.py in data/evaluation/geeks_for_geeks_successful_test_scripts/python |
40 | 1 | 14 |
REMOVE_CONSECUTIVE_DUPLICATES_STRING.py in data/evaluation/geeks_for_geeks_successful_test_scripts/python |
44 | 1 | 14 |
GIVEN_1S_2S_3S_KS_PRINT_ZIG_ZAG_WAY.py in data/evaluation/geeks_for_geeks_successful_test_scripts/python |
56 | 1 | 14 |
REARRANGE_ARRAY_MAXIMUM_MINIMUM_FORM_SET_2_O1_EXTRA_SPACE.py in data/evaluation/geeks_for_geeks_successful_test_scripts/python |
45 | 1 | 12 |
K_SMALLEST_ELEMENTS_ORDER_USING_O1_EXTRA_SPACE.py in data/evaluation/geeks_for_geeks_successful_test_scripts/python |
48 | 1 | 12 |
PROGRAM_BEST_FIT_ALGORITHM_MEMORY_MANAGEMENT.py in data/evaluation/geeks_for_geeks_successful_test_scripts/python |
52 | 1 | 12 |
PROGRAM_REVERSE_STRING_ITERATIVE_RECURSIVE.py in data/evaluation/geeks_for_geeks_successful_test_scripts/python |
38 | 1 | 12 |
SORT_ARRAY_APPLYING_GIVEN_EQUATION.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
157 | 2 | 12 |
REARRANGE_ARRAY_MAXIMUM_MINIMUM_FORM_SET_2_O1_EXTRA_SPACE.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
82 | 2 | 11 |
LONGEST_COMMON_SUBSTRING.java in data/evaluation/geeks_for_geeks_successful_test_scripts/java |
80 | 2 | 11 |
FIND_TRIPLETS_ARRAY_WHOSE_SUM_EQUAL_ZERO_2.py in data/evaluation/geeks_for_geeks_successful_test_scripts/python |
51 | 1 | 10 |
SORT_ARRAY_APPLYING_GIVEN_EQUATION.py in data/evaluation/geeks_for_geeks_successful_test_scripts/python |
65 | 1 | 10 |
THIRD_LARGEST_ELEMENT_ARRAY_DISTINCT_ELEMENTS.py in data/evaluation/geeks_for_geeks_successful_test_scripts/python |
50 | 1 | 10 |
ODD_EVEN_SORT_BRICK_SORT.py in data/evaluation/geeks_for_geeks_successful_test_scripts/python |
46 | 1 | 10 |
RECURSIVE_INSERTION_SORT.py in data/evaluation/geeks_for_geeks_successful_test_scripts/python |
42 | 1 | 10 |