Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 12 additions & 4 deletions .github/workflows/test.yml
Original file line number Diff line number Diff line change
Expand Up @@ -15,23 +15,31 @@ jobs:
strategy:
fail-fast: false
matrix:
python-version: ["3.7", "3.8", "3.9", "3.10"]
python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
pandas-version: ["latest"]
include:
# oldest pandas with DataFrame.map, and the last 2.x series
- python-version: "3.11"
pandas-version: "2.1.*"
- python-version: "3.12"
pandas-version: "2.2.*"

steps:
- uses: actions/checkout@v2
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v2
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install dependencies
run: |
python -m pip install --upgrade pip
python -m pip install flake8 pytest
if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
if [ "${{ matrix.pandas-version }}" != "latest" ]; then pip install "pandas==${{ matrix.pandas-version }}" "numpy<2"; fi
- name: Lint with flake8
run: |
# stop the build if there are Python syntax errors or undefined names
flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
- name: Test with unittest
run: |
python -m unittest
python -m unittest -v
41 changes: 22 additions & 19 deletions plot_likert/plot_likert.py
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,8 @@

Note:
the data must be strings
for a float: scores.applymap(int).applymap(str)
for a float: scores.map(int).map(str)
(with pandas < 2.1, use DataFrame.applymap instead of DataFrame.map)
"""


Expand Down Expand Up @@ -46,6 +47,18 @@ class PlotLikertError(ValueError):
pass


def _map_elements(df: pd.DataFrame, func) -> pd.DataFrame:
"""
Apply a function to every element of a DataFrame.

DataFrame.applymap was deprecated in pandas 2.1 (renamed to DataFrame.map)
and removed in pandas 3.0, so use whichever one is available.
"""
if hasattr(pd.DataFrame, "map"):
return df.map(func)
return df.applymap(func) # pandas < 2.1


def plot_counts(
counts: pd.DataFrame,
scale: Scale,
Expand Down Expand Up @@ -254,18 +267,14 @@ def validate(value):
f"A response was found with value `{value}`, which is not one of the values in the provided scale: {scale}. If this is unexpected, you might want to double-check for extra whitespace, capitalization, spelling, or type (int versus str)."
)

try:
df.map(validate)
except AttributeError: # for compatibility with Pandas < 2.1.0
df.applymap(validate)
_map_elements(df, validate)

# fix long questions for printing
old_labels = list(df)
new_labels = ["\n".join(wrap(str(l), label_max_width)) for l in old_labels]
if pd.__version__ >= "1.5.0":
df = df.set_axis(new_labels, axis=1, copy=True)
else:
df = df.set_axis(new_labels, axis=1, inplace=False)
# set_axis returns a new object by default (pandas >= 1.0); the `inplace` keyword
# was removed in pandas 2.0 and `copy` is deprecated in pandas 3.0, so pass neither
df = df.set_axis(new_labels, axis=1)

counts_unordered = df.apply(lambda row: row.value_counts())
counts = counts_unordered.reindex(scale).T
Expand Down Expand Up @@ -299,12 +308,9 @@ def likert_percentages(
"In your data, not all questions have the same number of responses. i.e., different numbers of people answered each question. Therefore, the percentages aren't directly comparable: X% for one question represents a different number of responses than X% for another question, yet they will appear the same in the percentage graph. This may be misleading to your reader."
)

try:
return counts.apply(lambda row: row / row.sum(), axis=1).map(lambda v: 100 * v)
except AttributeError: # for compatibility with Pandas < 2.1.0
return counts.apply(lambda row: row / row.sum(), axis=1).applymap(
lambda v: 100 * v
)
return _map_elements(
counts.apply(lambda row: row / row.sum(), axis=1), lambda v: 100 * v
)


def _compute_counts_percentage(counts: pd.DataFrame) -> pd.DataFrame:
Expand All @@ -331,10 +337,7 @@ def likert_response(df: pd.DataFrame, scale: Scale) -> pd.DataFrame:
orginal data.
"""
for i in range(0, len(scale)):
try:
df = df.map(lambda x: scale[i] if str(i) in x else x)
except AttributeError: # for compatibility with Pandas < 2.1.0
df = df.map(lambda x: scale[i] if str(i) in x else x)
df = _map_elements(df, lambda x: scale[i] if str(i) in x else x)
return df


Expand Down
154 changes: 154 additions & 0 deletions tests/test_pandas_compat.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,154 @@
"""
Regression tests for the data-handling functions and for compatibility with
current pandas versions (2.1+ and 3.x: DataFrame.map instead of applymap,
positional Series lookups via .iloc, the new default string dtype,
and no deprecated keyword arguments).
"""

import unittest
import warnings

import matplotlib

matplotlib.use("Agg") # no GUI needed for the tests
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

import plot_likert
from plot_likert.scales import agree


def sample_responses(index=None):
return pd.DataFrame(
{
"Q1": [agree[0], agree[1], agree[2], agree[3], agree[4], agree[4]],
"Q2": [agree[4], agree[4], agree[3], agree[2], agree[2], agree[0]],
},
index=index,
)


class PandasWarningsAsErrors(unittest.TestCase):
"""Fail on any deprecation warning raised while running a test."""

def setUp(self):
self._warnings = warnings.catch_warnings()
self._warnings.__enter__()
warnings.simplefilter("error", DeprecationWarning)
warnings.simplefilter("error", FutureWarning)
try: # pandas 3 has its own deprecation warning classes
from pandas.errors import PandasChangeWarning

warnings.simplefilter("error", PandasChangeWarning)
except ImportError:
pass

def tearDown(self):
self._warnings.__exit__(None, None, None)
plt.close("all")


class TestLikertCounts(PandasWarningsAsErrors):
def test_counts_dataframe(self):
counts = plot_likert.likert_counts(sample_responses(), agree)
self.assertEqual(list(counts.columns), list(agree))
self.assertEqual(list(counts.index), ["Q1", "Q2"])
self.assertEqual(counts.loc["Q1"].tolist(), [1, 1, 1, 1, 2])
self.assertEqual(counts.loc["Q2"].tolist(), [1, 0, 2, 1, 2])

def test_counts_series(self):
counts = plot_likert.likert_counts(sample_responses()["Q1"], agree)
self.assertEqual(counts.loc["Q1"].tolist(), [1, 1, 1, 1, 2])

def test_counts_with_missing_values(self):
df = sample_responses()
df.loc[0, "Q1"] = np.nan
counts = plot_likert.likert_counts(df, agree)
self.assertEqual(counts.loc["Q1"].tolist(), [0, 1, 1, 1, 2])

def test_counts_explicit_string_dtype(self):
counts = plot_likert.likert_counts(sample_responses().astype("string"), agree)
self.assertEqual(counts.loc["Q2"].tolist(), [1, 0, 2, 1, 2])

def test_long_labels_are_wrapped(self):
df = sample_responses().rename(columns={"Q1": "a " * 30})
counts = plot_likert.likert_counts(df, agree, label_max_width=10)
self.assertIn("\n", counts.index[0])

def test_input_is_not_modified(self):
df = sample_responses()
plot_likert.likert_counts(df, agree, label_max_width=1)
self.assertEqual(list(df.columns), ["Q1", "Q2"])

def test_invalid_value_raises(self):
df = sample_responses()
df.loc[0, "Q1"] = "Maybe"
with self.assertRaises(plot_likert.PlotLikertError):
plot_likert.likert_counts(df, agree)

def test_numeric_responses_with_numeric_scale(self):
df = pd.DataFrame({"Q1": [1, 2, 3, 4, 5, 5]})
counts = plot_likert.likert_counts(df, [1, 2, 3, 4, 5])
self.assertEqual(counts.loc["Q1"].tolist(), [1, 1, 1, 1, 2])


class TestLikertPercentages(PandasWarningsAsErrors):
def test_percentages(self):
pct = plot_likert.likert_percentages(sample_responses(), agree)
self.assertAlmostEqual(pct.loc["Q1", agree[4]], 100 * 2 / 6)
np.testing.assert_allclose(pct.sum(axis=1).to_numpy(), [100, 100])

def test_percentages_non_integer_index(self):
# pandas 3: Series[0] is a label lookup, so the first row must be read with .iloc
df = sample_responses(index=list("abcdef"))
pct = plot_likert.likert_percentages(df, agree)
np.testing.assert_allclose(pct.sum(axis=1).to_numpy(), [100, 100])

def test_unequal_response_counts_warn(self):
df = sample_responses()
df.loc[0, "Q1"] = np.nan
with self.assertWarns(UserWarning):
plot_likert.likert_percentages(df, agree)


class TestLikertResponse(PandasWarningsAsErrors):
def test_numeric_codes_replaced_by_scale(self):
df = pd.DataFrame({"Q1": ["1", "2", "3"], "Q2": ["3", "3", "1"]})
result = plot_likert.likert_response(df, ["zero", "one", "two", "three"])
self.assertEqual(result["Q1"].tolist(), ["one", "two", "three"])
self.assertEqual(result["Q2"].tolist(), ["three", "three", "one"])


class TestPlotting(PandasWarningsAsErrors):
def test_plot_likert(self):
ax = plot_likert.plot_likert(sample_responses(), agree)
self.assertEqual(len(ax.patches), 2 * (len(agree) + 1))

def test_plot_likert_percentages_and_bar_labels(self):
ax = plot_likert.plot_likert(
sample_responses(), agree, plot_percentage=True, bar_labels=True
)
self.assertEqual(ax.get_xlabel(), "Percentage of Responses")

def test_plot_likert_series(self):
ax = plot_likert.plot_likert(sample_responses()["Q2"], agree)
self.assertEqual(len(ax.patches), len(agree) + 1)

def test_plot_likert_format_scale(self):
df = pd.DataFrame({"Q1": ["1", "2", "3", "4", "5"]})
ax = plot_likert.plot_likert(df, agree, format_scale=["NA"] + list(agree))
self.assertEqual(ax.get_xlabel(), "Number of Responses")

def test_plot_counts_non_integer_index(self):
counts = pd.DataFrame(
[[1, 2, 4, 2, 1], [2, 2, 2, 2, 2]],
columns=agree,
index=["first question", "second question"],
)
ax = plot_likert.plot_counts(counts, agree, compute_percentages=True)
self.assertEqual(ax.get_xlabel(), "Percentage of Responses")


if __name__ == "__main__":
unittest.main()