+49
-5
lines changedFilter options
+49
-5
lines changed Original file line number Diff line number Diff line change
@@ -20,7 +20,7 @@
20 20 21 21 22 22
def get_character_counts_vc(vc: pd.Series) -> pd.Series:
23 -
series = pd.Series(vc.index, index=vc)
23 +
series = pd.Series(vc.index, index=vc, dtype=object)
24 24
characters = series[series != ""].apply(list)
25 25
characters = characters.explode()
26 26
@@ -170,7 +170,7 @@ def word_summary_vc(vc: pd.Series, stop_words: List[str] = []) -> dict:
170 170
# TODO: configurable lowercase/punctuation etc.
171 171
# TODO: remove punctuation in words
172 172 173 -
series = pd.Series(vc.index, index=vc)
173 +
series = pd.Series(vc.index, index=vc, dtype=object)
174 174
word_lists = series.str.lower().str.split()
175 175
words = word_lists.explode().str.strip(string.punctuation + string.whitespace)
176 176
word_counts = pd.Series(words.index, index=words)
@@ -188,7 +188,7 @@ def word_summary_vc(vc: pd.Series, stop_words: List[str] = []) -> dict:
188 188 189 189 190 190
def length_summary_vc(vc: pd.Series) -> dict:
191 -
series = pd.Series(vc.index, index=vc)
191 +
series = pd.Series(vc.index, index=vc, dtype=object)
192 192
length = series.str.len()
193 193
length_counts = pd.Series(length.index, index=length)
194 194
length_counts = length_counts.groupby(level=0, sort=False).sum()
@@ -10,6 +10,7 @@
10 10 11 11
from ydata_profiling.config import Settings
12 12
from ydata_profiling.model.typeset import ProfilingTypeSet
13 +
from ydata_profiling.utils.compat import optional_option_context
13 14
from ydata_profiling.utils.dataframe import sort_column_names
14 15 15 16
BaseSummarizer: Any = "BaseSummarizer" # type: ignore
@@ -38,7 +39,8 @@ def pandas_describe_1d(
38 39
"""
39 40 40 41
# Make sure pd.NA is not in the series
41 -
series = series.fillna(np.nan)
42 +
with optional_option_context("future.no_silent_downcasting", True):
43 +
series = series.fillna(np.nan).infer_objects(copy=False)
42 44 43 45
has_cast_type = _is_cast_type_defined(typeset, series.name) # type:ignore
44 46
cast_type = (
@@ -1,6 +1,8 @@
1 1
"""Utility functions for (version) compatibility"""
2 + 3 +
from contextlib import contextmanager
2 4
from functools import lru_cache
3 -
from typing import Tuple
5 +
from typing import Generator, Tuple
4 6 5 7
import pandas as pd
6 8
@@ -12,3 +14,18 @@ def pandas_version_info() -> Tuple[int, ...]:
12 14
akin to `sys.version_info` for the Python version.
13 15
"""
14 16
return tuple(int(s) for s in pd.__version__.split("."))
17 + 18 + 19 +
@contextmanager
20 +
def optional_option_context(
21 +
option_key: str, value: object
22 +
) -> Generator[None, None, None]:
23 +
"""
24 +
A context manager that sets an option only if it is available in the
25 +
current pandas version; otherwise, it is a no-op.
26 +
"""
27 +
try:
28 +
with pd.option_context(option_key, value):
29 +
yield
30 +
except pd.errors.OptionError:
31 +
yield
Original file line number Diff line number Diff line change
@@ -0,0 +1,25 @@
1 +
import pandas as pd
2 +
import pytest
3 + 4 +
from ydata_profiling import ProfileReport
5 +
from ydata_profiling.utils.compat import pandas_version_info
6 + 7 + 8 +
@pytest.fixture()
9 +
def df():
10 +
df = pd.DataFrame(
11 +
{
12 +
"foo": [1, 2, 3],
13 +
"bar": ["", "", ""],
14 +
}
15 +
)
16 +
return df
17 + 18 + 19 +
@pytest.mark.skipif(
20 +
pandas_version_info() < (2, 1, 0), reason="requires pandas 2.1 or higher"
21 +
)
22 +
def test_pd_future_infer_string(df: pd.DataFrame):
23 +
with pd.option_context("future.infer_string", True):
24 +
profile_report = ProfileReport(df, title="Test Report", progress_bar=False)
25 +
assert len(profile_report.to_html()) > 0
You can’t perform that action at this time.
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4