csv-detective 0.9.3.dev2456__py3-none-any.whl → 0.9.3.dev2486__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- csv_detective/parsing/csv.py +1 -1
- csv_detective/parsing/excel.py +2 -2
- {csv_detective-0.9.3.dev2456.dist-info → csv_detective-0.9.3.dev2486.dist-info}/METADATA +1 -1
- {csv_detective-0.9.3.dev2456.dist-info → csv_detective-0.9.3.dev2486.dist-info}/RECORD +6 -6
- {csv_detective-0.9.3.dev2456.dist-info → csv_detective-0.9.3.dev2486.dist-info}/WHEEL +0 -0
- {csv_detective-0.9.3.dev2456.dist-info → csv_detective-0.9.3.dev2486.dist-info}/entry_points.txt +0 -0
csv_detective/parsing/csv.py
CHANGED
|
@@ -42,7 +42,7 @@ def parse_csv(
|
|
|
42
42
|
logging.warning(f"File is too long, analysing in chunks of {CHUNK_SIZE} rows")
|
|
43
43
|
total_lines, nb_duplicates = None, None
|
|
44
44
|
else:
|
|
45
|
-
nb_duplicates =
|
|
45
|
+
nb_duplicates = table.duplicated().sum()
|
|
46
46
|
if num_rows > 0:
|
|
47
47
|
num_rows = min(num_rows, total_lines or len(table))
|
|
48
48
|
table = table.sample(num_rows, random_state=random_state)
|
csv_detective/parsing/excel.py
CHANGED
|
@@ -124,7 +124,7 @@ def parse_excel(
|
|
|
124
124
|
)
|
|
125
125
|
table, header_row_idx = remove_empty_first_rows(table)
|
|
126
126
|
total_lines = len(table)
|
|
127
|
-
nb_duplicates =
|
|
127
|
+
nb_duplicates = table.duplicated().sum()
|
|
128
128
|
if num_rows > 0:
|
|
129
129
|
num_rows = min(num_rows - 1, total_lines)
|
|
130
130
|
table = table.sample(num_rows, random_state=random_state)
|
|
@@ -155,7 +155,7 @@ def parse_excel(
|
|
|
155
155
|
)
|
|
156
156
|
table, header_row_idx = remove_empty_first_rows(table)
|
|
157
157
|
total_lines = len(table)
|
|
158
|
-
nb_duplicates =
|
|
158
|
+
nb_duplicates = table.duplicated().sum()
|
|
159
159
|
if num_rows > 0:
|
|
160
160
|
num_rows = min(num_rows - 1, total_lines)
|
|
161
161
|
table = table.sample(num_rows, random_state=random_state)
|
|
@@ -80,13 +80,13 @@ csv_detective/output/utils.py,sha256=tbji3dEH7bDc6gLCeVSVquqU3xaHA1CQOMuaJT4Hub8
|
|
|
80
80
|
csv_detective/parsing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
81
81
|
csv_detective/parsing/columns.py,sha256=WwivsR4r-SAkugzVSmYeUkgbNXz3CWXnEl2ZmoX_tcs,9238
|
|
82
82
|
csv_detective/parsing/compression.py,sha256=Fnw5tj-PpBNI8NYsWj5gD-DUoWcVLnsVpiKm9MpxmIA,350
|
|
83
|
-
csv_detective/parsing/csv.py,sha256=
|
|
84
|
-
csv_detective/parsing/excel.py,sha256=
|
|
83
|
+
csv_detective/parsing/csv.py,sha256=5rw6gXZFQC1T4NT9CnW0AumidrYOkF8kjrfWGmk949I,1716
|
|
84
|
+
csv_detective/parsing/excel.py,sha256=tb65I78tdYlZci_tzvvQt8U6bZSYKjeVdn2CEvsET1o,6972
|
|
85
85
|
csv_detective/parsing/load.py,sha256=f-8aKiNpy_47qg4Lq-UZUR4NNrbJ_-KEGvcUQZ8cmb0,4317
|
|
86
86
|
csv_detective/parsing/text.py,sha256=uz8wfmNTQnOd_4fjrIZ_5rxmFmgrg343hJh2szB73Hc,1770
|
|
87
87
|
csv_detective/utils.py,sha256=RJ_zFOJ1DRY8HtDrKPiCdNk5gU6-KwOrOKOyfSkBZZY,1118
|
|
88
88
|
csv_detective/validate.py,sha256=CjZXhhDP-n6wGgEqbwrGRqebU8L5bidwnvQp-TbnvFA,5424
|
|
89
|
-
csv_detective-0.9.3.
|
|
90
|
-
csv_detective-0.9.3.
|
|
91
|
-
csv_detective-0.9.3.
|
|
92
|
-
csv_detective-0.9.3.
|
|
89
|
+
csv_detective-0.9.3.dev2486.dist-info/WHEEL,sha256=z-mOpxbJHqy3cq6SvUThBZdaLGFZzdZPtgWLcP2NKjQ,79
|
|
90
|
+
csv_detective-0.9.3.dev2486.dist-info/entry_points.txt,sha256=1J86TQNCanjsLMboAufdEUla03qEQaC9QmVGYgt2FCQ,57
|
|
91
|
+
csv_detective-0.9.3.dev2486.dist-info/METADATA,sha256=XOx2vmkCJGFTCAc0znJ3bcz7V9mAtq7qXqh0GF8ERys,11063
|
|
92
|
+
csv_detective-0.9.3.dev2486.dist-info/RECORD,,
|
|
File without changes
|
{csv_detective-0.9.3.dev2456.dist-info → csv_detective-0.9.3.dev2486.dist-info}/entry_points.txt
RENAMED
|
File without changes
|