deepseek-ai/DeepSeek-Coder
File Size
The distribution of size of files (measured in lines of code).
File Size Overall
  • There are 35 files with 6,386 lines of code.
    • 0 very long files (0 lines of code)
    • 6 long files (3,326 lines of code)
    • 5 medium size files (1,393 lines of code)
    • 9 small files (1,211 lines of code)
    • 15 very small files (456 lines of code)
0% | 52% | 21% | 18% | 7%
Legend:
1001+
501-1000
201-500
101-200
1-100


explore: grouped by folders | grouped by size | sunburst | 3D view
File Size per Extension
1001+
501-1000
201-500
101-200
1-100
jsonl0% | 80% | 19% | 0% | 0%
py0% | 38% | 23% | 28% | 10%
File Size per Logical Decomposition
primary
1001+
501-1000
201-500
101-200
1-100
Evaluation0% | 53% | 22% | 16% | 7%
finetune0% | 0% | 0% | 100% | 0%
Longest Files (Top 35)
File# lines# units
jsonl
multiarith.jsonl
in Evaluation/PAL-Math/datasets/mawps
 600 -
jsonl
singleop.jsonl
in Evaluation/PAL-Math/datasets/mawps
 562 -
execution.py
in Evaluation/HumanEval/human_eval
 552 11
execution.py
in Evaluation/LeetCode/human_eval
 552 11
execution.py
in Evaluation/MBPP/human_eval
 552 11
jsonl
singleeq.jsonl
in Evaluation/PAL-Math/datasets/mawps
 508 -
jsonl
addsub.jsonl
in Evaluation/PAL-Math/datasets/mawps
 395 -
evaluation.py
in Evaluation/LeetCode/human_eval
 264 6
evaluation.py
in Evaluation/HumanEval/human_eval
 250 6
evaluation.py
in Evaluation/MBPP/human_eval
 247 6
parser.py
in Evaluation/PAL-Math/utils
 237 10
mbpp.py
in Evaluation/MBPP
 180 6
152 7
python_executor.py
in Evaluation/PAL-Math/utils
 147 12
run.py
in Evaluation/PAL-Math
 142 4
humaneval.py
in Evaluation/HumanEval
 139 4
utils.py
in Evaluation/HumanEval/utils
 121 5
eval_instruct.py
in Evaluation/MBPP
 114 4
grader.py
in Evaluation/PAL-Math/utils
 109 7
eval_instruct.py
in Evaluation/HumanEval
 107 4
evaluate_leetcode.py
in Evaluation/LeetCode
 70 2
vllm_inference.py
in Evaluation/LeetCode
 67 2
dataset.py
in Evaluation/MBPP/utils
 38 4
dataset.py
in Evaluation/HumanEval/utils
 37 4
eval_pal.py
in Evaluation/HumanEval
 35 -
data.py
in Evaluation/HumanEval/human_eval
 35 3
data.py
in Evaluation/LeetCode/human_eval
 35 3
data.py
in Evaluation/MBPP/human_eval
 35 3
eval_pal.py
in Evaluation/MBPP
 33 -
utils.py
in Evaluation/MBPP/utils
 32 3
evaluate_functional_correctness.py
in Evaluation/HumanEval/human_eval
 18 2
evaluate_functional_correctness.py
in Evaluation/MBPP/human_eval
 18 2
__init__.py
in Evaluation/HumanEval/human_eval
 1 -
__init__.py
in Evaluation/LeetCode/human_eval
 1 -
__init__.py
in Evaluation/MBPP/human_eval
 1 -
Files With Most Units (Top 26)
File# lines# units
python_executor.py
in Evaluation/PAL-Math/utils
 147 12
execution.py
in Evaluation/HumanEval/human_eval
 552 11
execution.py
in Evaluation/LeetCode/human_eval
 552 11
execution.py
in Evaluation/MBPP/human_eval
 552 11
parser.py
in Evaluation/PAL-Math/utils
 237 10
152 7
grader.py
in Evaluation/PAL-Math/utils
 109 7
evaluation.py
in Evaluation/HumanEval/human_eval
 250 6
evaluation.py
in Evaluation/LeetCode/human_eval
 264 6
mbpp.py
in Evaluation/MBPP
 180 6
evaluation.py
in Evaluation/MBPP/human_eval
 247 6
utils.py
in Evaluation/HumanEval/utils
 121 5
eval_instruct.py
in Evaluation/HumanEval
 107 4
dataset.py
in Evaluation/HumanEval/utils
 37 4
humaneval.py
in Evaluation/HumanEval
 139 4
run.py
in Evaluation/PAL-Math
 142 4
eval_instruct.py
in Evaluation/MBPP
 114 4
dataset.py
in Evaluation/MBPP/utils
 38 4
data.py
in Evaluation/HumanEval/human_eval
 35 3
data.py
in Evaluation/LeetCode/human_eval
 35 3
data.py
in Evaluation/MBPP/human_eval
 35 3
utils.py
in Evaluation/MBPP/utils
 32 3
evaluate_functional_correctness.py
in Evaluation/HumanEval/human_eval
 18 2
evaluate_leetcode.py
in Evaluation/LeetCode
 70 2
vllm_inference.py
in Evaluation/LeetCode
 67 2
evaluate_functional_correctness.py
in Evaluation/MBPP/human_eval
 18 2
Files With Long Lines (Top 21)

There are 21 files with lines longer than 120 characters. In total, there are 1773 long lines.

File# lines# units# long lines
jsonl
multiarith.jsonl
in Evaluation/PAL-Math/datasets/mawps
 600 - 600
jsonl
singleeq.jsonl
in Evaluation/PAL-Math/datasets/mawps
 508 - 430
jsonl
addsub.jsonl
in Evaluation/PAL-Math/datasets/mawps
 395 - 372
jsonl
singleop.jsonl
in Evaluation/PAL-Math/datasets/mawps
 562 - 331
humaneval.py
in Evaluation/HumanEval
 139 4 6
mbpp.py
in Evaluation/MBPP
 180 6 5
execution.py
in Evaluation/HumanEval/human_eval
 552 11 3
execution.py
in Evaluation/LeetCode/human_eval
 552 11 3
vllm_inference.py
in Evaluation/LeetCode
 67 2 3
grader.py
in Evaluation/PAL-Math/utils
 109 7 3
execution.py
in Evaluation/MBPP/human_eval
 552 11 3
152 7 2
eval_pal.py
in Evaluation/HumanEval
 35 - 2
run.py
in Evaluation/PAL-Math
 142 4 2
eval_pal.py
in Evaluation/MBPP
 33 - 2
eval_instruct.py
in Evaluation/HumanEval
 107 4 1
evaluation.py
in Evaluation/HumanEval/human_eval
 250 6 1
utils.py
in Evaluation/HumanEval/utils
 121 5 1
evaluation.py
in Evaluation/MBPP/human_eval
 247 6 1
dataset.py
in Evaluation/MBPP/utils
 38 4 1
utils.py
in Evaluation/MBPP/utils
 32 3 1
Correlations

File Size vs. Commits (all time): 12 points

Evaluation/LeetCode/evaluate_leetcode.py x: 2 commits (all time) y: 70 lines of code Evaluation/LeetCode/human_eval/__init__.py x: 2 commits (all time) y: 1 lines of code Evaluation/LeetCode/human_eval/data.py x: 2 commits (all time) y: 35 lines of code Evaluation/LeetCode/human_eval/evaluation.py x: 2 commits (all time) y: 264 lines of code Evaluation/LeetCode/human_eval/execution.py x: 2 commits (all time) y: 552 lines of code Evaluation/LeetCode/vllm_inference.py x: 2 commits (all time) y: 67 lines of code Evaluation/HumanEval/eval_instruct.py x: 8 commits (all time) y: 107 lines of code Evaluation/MBPP/eval_instruct.py x: 4 commits (all time) y: 114 lines of code Evaluation/PAL-Math/run.py x: 1 commits (all time) y: 142 lines of code Evaluation/MBPP/human_eval/evaluation.py x: 2 commits (all time) y: 247 lines of code finetune/finetune_deepseekcoder.py x: 3 commits (all time) y: 152 lines of code Evaluation/HumanEval/utils/utils.py x: 2 commits (all time) y: 121 lines of code
552.0
lines of code
  min: 1.0
  average: 156.0
  25th percentile: 67.75
  median: 117.5
  75th percentile: 223.25
  max: 552.0
0 8.0
commits (all time)
min: 1.0 | average: 2.67 | 25th percentile: 2.0 | median: 2.0 | 75th percentile: 2.75 | max: 8.0

File Size vs. Contributors (all time): 12 points

Evaluation/LeetCode/evaluate_leetcode.py x: 1 contributors (all time) y: 70 lines of code Evaluation/LeetCode/human_eval/__init__.py x: 1 contributors (all time) y: 1 lines of code Evaluation/LeetCode/human_eval/data.py x: 1 contributors (all time) y: 35 lines of code Evaluation/LeetCode/human_eval/evaluation.py x: 1 contributors (all time) y: 264 lines of code Evaluation/LeetCode/human_eval/execution.py x: 1 contributors (all time) y: 552 lines of code Evaluation/LeetCode/vllm_inference.py x: 1 contributors (all time) y: 67 lines of code Evaluation/HumanEval/eval_instruct.py x: 5 contributors (all time) y: 107 lines of code Evaluation/MBPP/eval_instruct.py x: 2 contributors (all time) y: 114 lines of code Evaluation/PAL-Math/run.py x: 1 contributors (all time) y: 142 lines of code Evaluation/MBPP/human_eval/evaluation.py x: 2 contributors (all time) y: 247 lines of code finetune/finetune_deepseekcoder.py x: 2 contributors (all time) y: 152 lines of code Evaluation/HumanEval/utils/utils.py x: 2 contributors (all time) y: 121 lines of code
552.0
lines of code
  min: 1.0
  average: 156.0
  25th percentile: 67.75
  median: 117.5
  75th percentile: 223.25
  max: 552.0
0 5.0
contributors (all time)
min: 1.0 | average: 1.67 | 25th percentile: 1.0 | median: 1.0 | 75th percentile: 2.0 | max: 5.0

File Size vs. Commits (30 days): 0 points

No data for "commits (30d)" vs. "lines of code".

File Size vs. Contributors (30 days): 0 points

No data for "contributors (30d)" vs. "lines of code".

File Size vs. Commits (90 days): 0 points

No data for "commits (90d)" vs. "lines of code".

File Size vs. Contributors (90 days): 0 points

No data for "contributors (90d)" vs. "lines of code".

About This Analysis
  • File size measurements show the distribution of size of files.
  • Files are classified in four categories based on their size (lines of code): 1-100 (very small files), 101-200 (small files), 201-500 (medium size files), 501-1000 (long files), 1001+(very long files).
  • It is a good practice to keep files small. Long files may become "bloaters", code that have increased to such gargantuan proportions that they are hard to work with.
Learn more...