Merge branch 'main' into depr-sparse-astype

Author: jbrockmendel

asv_bench/asv.conf.json

@@ -54,7 +54,6 @@
         "openpyxl": [],
         "xlsxwriter": [],
         "xlrd": [],
-        "xlwt": [],
         "odfpy": [],
         "jinja2": [],
     },

asv_bench/benchmarks/io/excel.py

@@ -33,7 +33,7 @@ def _generate_dataframe():
 
 class WriteExcel:
 
-    params = ["openpyxl", "xlsxwriter", "xlwt"]
+    params = ["openpyxl", "xlsxwriter"]
     param_names = ["engine"]
 
     def setup(self, engine):
@@ -68,10 +68,9 @@ def time_write_excel_style(self, engine):
 
 class ReadExcel:
 
-    params = ["xlrd", "openpyxl", "odf"]
+    params = ["openpyxl", "odf"]
     param_names = ["engine"]
     fname_excel = "spreadsheet.xlsx"
-    fname_excel_xls = "spreadsheet.xls"
     fname_odf = "spreadsheet.ods"
 
     def _create_odf(self):
@@ -92,13 +91,10 @@ def setup_cache(self):
         self.df = _generate_dataframe()
 
         self.df.to_excel(self.fname_excel, sheet_name="Sheet1")
-        self.df.to_excel(self.fname_excel_xls, sheet_name="Sheet1")
         self._create_odf()
 
     def time_read_excel(self, engine):
-        if engine == "xlrd":
-            fname = self.fname_excel_xls
-        elif engine == "odf":
+        if engine == "odf":
             fname = self.fname_odf
         else:
             fname = self.fname_excel
@@ -107,9 +103,7 @@ def time_read_excel(self, engine):
 
 class ReadExcelNRows(ReadExcel):
     def time_read_excel(self, engine):
-        if engine == "xlrd":
-            fname = self.fname_excel_xls
-        elif engine == "odf":
+        if engine == "odf":
             fname = self.fname_odf
         else:
             fname = self.fname_excel

asv_bench/benchmarks/io/sql.py

@@ -38,7 +38,7 @@ def setup(self, connection):
             },
             index=tm.makeStringIndex(N),
         )
-        self.df.loc[1000:3000, "float_with_nan"] = np.nan
+        self.df.iloc[1000:3000, 1] = np.nan
         self.df["date"] = self.df["datetime"].dt.date
         self.df["time"] = self.df["datetime"].dt.time
         self.df["datetime_string"] = self.df["datetime"].astype(str)
@@ -88,7 +88,7 @@ def setup(self, connection, dtype):
             },
             index=tm.makeStringIndex(N),
         )
-        self.df.loc[1000:3000, "float_with_nan"] = np.nan
+        self.df.iloc[1000:3000, 1] = np.nan
         self.df["date"] = self.df["datetime"].dt.date
         self.df["time"] = self.df["datetime"].dt.time
         self.df["datetime_string"] = self.df["datetime"].astype(str)
@@ -117,7 +117,7 @@ def setup(self):
             },
             index=tm.makeStringIndex(N),
         )
-        self.df.loc[1000:3000, "float_with_nan"] = np.nan
+        self.df.iloc[1000:3000, 1] = np.nan
         self.df["date"] = self.df["datetime"].dt.date
         self.df["time"] = self.df["datetime"].dt.time
         self.df["datetime_string"] = self.df["datetime"].astype(str)
@@ -164,7 +164,7 @@ def setup(self, dtype):
             },
             index=tm.makeStringIndex(N),
         )
-        self.df.loc[1000:3000, "float_with_nan"] = np.nan
+        self.df.iloc[1000:3000, 1] = np.nan
         self.df["date"] = self.df["datetime"].dt.date
         self.df["time"] = self.df["datetime"].dt.time
         self.df["datetime_string"] = self.df["datetime"].astype(str)

asv_bench/benchmarks/reshape.py

@@ -36,7 +36,7 @@ def setup(self):
         self.df = DataFrame(data)
 
     def time_reshape_pivot_time_series(self):
-        self.df.pivot("date", "variable", "value")
+        self.df.pivot(index="date", columns="variable", values="value")
 
 
 class SimpleReshape:

ci/code_checks.sh

@@ -47,7 +47,7 @@ import pandas
 
 blocklist = {'bs4', 'gcsfs', 'html5lib', 'http', 'ipython', 'jinja2', 'hypothesis',
              'lxml', 'matplotlib', 'openpyxl', 'py', 'pytest', 's3fs', 'scipy',
-             'tables', 'urllib.request', 'xlrd', 'xlsxwriter', 'xlwt'}
+             'tables', 'urllib.request', 'xlrd', 'xlsxwriter'}
 
 # GH#28227 for some of these check for top-level modules, while others are
 #  more specific (e.g. urllib.request)

ci/deps/actions-310.yaml

@@ -51,5 +51,4 @@ dependencies:
   - xarray
   - xlrd
   - xlsxwriter
-  - xlwt
   - zstandard

ci/deps/actions-38-downstream_compat.yaml

@@ -51,7 +51,6 @@ dependencies:
   - xarray
   - xlrd
   - xlsxwriter
-  - xlwt
   - zstandard
 
   # downstream packages

ci/deps/actions-38-minimum_versions.yaml

@@ -53,5 +53,4 @@ dependencies:
   - xarray=0.19.0
   - xlrd=2.0.1
   - xlsxwriter=1.4.3
-  - xlwt=1.3.0
   - zstandard=0.15.2

ci/deps/actions-38.yaml

@@ -50,5 +50,4 @@ dependencies:
   - xarray
   - xlrd
   - xlsxwriter
-  - xlwt
   - zstandard

ci/deps/actions-39.yaml

@@ -51,5 +51,4 @@ dependencies:
   - xarray
   - xlrd
   - xlsxwriter
-  - xlwt
   - zstandard

ci/deps/circle-38-arm64.yaml

@@ -51,5 +51,4 @@ dependencies:
   - xarray
   - xlrd
   - xlsxwriter
-  - xlwt
   - zstandard

doc/scripts/eval_performance.py

@@ -0,0 +1,108 @@
+from timeit import repeat as timeit
+
+import numpy as np
+import seaborn as sns
+
+from pandas import DataFrame
+
+setup_common = """from pandas import DataFrame
+from numpy.random import randn
+df = DataFrame(randn(%d, 3), columns=list('abc'))
+%s"""
+
+setup_with = "s = 'a + b * (c ** 2 + b ** 2 - a) / (a * c) ** 3'"
+
+
+def bench_with(n, times=10, repeat=3, engine="numexpr"):
+    return (
+        np.array(
+            timeit(
+                "df.eval(s, engine=%r)" % engine,
+                setup=setup_common % (n, setup_with),
+                repeat=repeat,
+                number=times,
+            )
+        )
+        / times
+    )
+
+
+setup_subset = "s = 'a <= b <= c ** 2 + b ** 2 - a and b > c'"
+
+
+def bench_subset(n, times=20, repeat=3, engine="numexpr"):
+    return (
+        np.array(
+            timeit(
+                "df.query(s, engine=%r)" % engine,
+                setup=setup_common % (n, setup_subset),
+                repeat=repeat,
+                number=times,
+            )
+        )
+        / times
+    )
+
+
+def bench(mn=3, mx=7, num=100, engines=("python", "numexpr"), verbose=False):
+    r = np.logspace(mn, mx, num=num).round().astype(int)
+
+    ev = DataFrame(np.empty((num, len(engines))), columns=engines)
+    qu = ev.copy(deep=True)
+
+    ev["size"] = qu["size"] = r
+
+    for engine in engines:
+        for i, n in enumerate(r):
+            if verbose & (i % 10 == 0):
+                print("engine: %r, i == %d" % (engine, i))
+            ev_times = bench_with(n, times=1, repeat=1, engine=engine)
+            ev.loc[i, engine] = np.mean(ev_times)
+            qu_times = bench_subset(n, times=1, repeat=1, engine=engine)
+            qu.loc[i, engine] = np.mean(qu_times)
+
+    return ev, qu
+
+
+def plot_perf(df, engines, title, filename=None):
+    from matplotlib.pyplot import figure
+
+    sns.set()
+    sns.set_palette("Set2")
+
+    fig = figure(figsize=(4, 3), dpi=120)
+    ax = fig.add_subplot(111)
+
+    for engine in engines:
+        ax.loglog(df["size"], df[engine], label=engine, lw=2)
+
+    ax.set_xlabel("Number of Rows")
+    ax.set_ylabel("Time (s)")
+    ax.set_title(title)
+    ax.legend(loc="best")
+    ax.tick_params(top=False, right=False)
+
+    fig.tight_layout()
+
+    if filename is not None:
+        fig.savefig(filename)
+
+
+if __name__ == "__main__":
+    import os
+
+    pandas_dir = os.path.dirname(
+        os.path.dirname(os.path.abspath(os.path.dirname(__file__)))
+    )
+    static_path = os.path.join(pandas_dir, "doc", "source", "_static")
+
+    join = lambda p: os.path.join(static_path, p)
+
+    fn = join("eval-query-perf-data.h5")
+
+    engines = "python", "numexpr"
+
+    ev, qu = bench(verbose=True)  # only this one
+
+    plot_perf(ev, engines, "DataFrame.eval()", filename=join("eval-perf.png"))
+    plot_perf(qu, engines, "DataFrame.query()", filename=join("query-perf.png"))

doc/source/_static/eval-perf-small.png

@@ -236,7 +236,7 @@
 if ".dev" in version:
     switcher_version = "dev"
 elif "rc" in version:
-    switcher_version = version.split("rc")[0] + " (rc)"
+    switcher_version = version.split("rc", maxsplit=1)[0] + " (rc)"
 
 html_theme_options = {
     "external_links": [],

doc/source/_static/eval-perf.png

@@ -10,7 +10,7 @@ To test out code changes, you'll need to build pandas from source, which
 requires a C/C++ compiler and Python environment. If you're making documentation
 changes, you can skip to :ref:`contributing to the documentation <contributing_documentation>` but if you skip
 creating the development environment you won't be able to build the documentation
-locally before pushing your changes.
+locally before pushing your changes. It's recommended to also install the :ref:`pre-commit hooks <contributing.pre-commit>`.
 
 .. contents:: Table of contents:
    :local:

doc/source/_static/query-perf-small.png

@@ -336,7 +336,6 @@ Can be managed as optional_extra with ``pandas[excel]``.
 Dependency                Minimum Version    optional_extra  Notes
 ========================= ================== =============== =============================================================
 xlrd                      2.0.1              excel           Reading Excel
-xlwt                      1.3.0              excel           Writing Excel
 xlsxwriter                1.4.3              excel           Writing Excel
 openpyxl                  3.0.7              excel           Reading / writing for xlsx files
 pyxlsb                    1.0.8              excel           Reading for xlsb files

doc/source/_static/query-perf.png

@@ -144,7 +144,7 @@ I want to add a new column to the ``DataFrame`` containing only the month of the
 
 By using ``Timestamp`` objects for dates, a lot of time-related
 properties are provided by pandas. For example the ``month``, but also
-``year``, ``weekofyear``, ``quarter``,… All of these properties are
+``year``, ``quarter``,… All of these properties are
 accessible by the ``dt`` accessor.
 
 .. raw:: html

doc/source/conf.py

@@ -343,8 +343,6 @@ Time/date components
    DatetimeIndex.timetz
    DatetimeIndex.dayofyear
    DatetimeIndex.day_of_year
-   DatetimeIndex.weekofyear
-   DatetimeIndex.week
    DatetimeIndex.dayofweek
    DatetimeIndex.day_of_week
    DatetimeIndex.weekday

doc/source/development/contributing_environment.rst

@@ -311,8 +311,6 @@ Datetime properties
    Series.dt.second
    Series.dt.microsecond
    Series.dt.nanosecond
-   Series.dt.week
-   Series.dt.weekofyear
    Series.dt.dayofweek
    Series.dt.day_of_week
    Series.dt.weekday

doc/source/getting_started/install.rst

@@ -353,11 +353,6 @@ Renaming categories is done by using the
 
     In contrast to R's ``factor``, categorical data can have categories of other types than string.
 
-.. note::
-
-    Be aware that assigning new categories is an inplace operation, while most other operations
-    under ``Series.cat`` per default return a new ``Series`` of dtype ``category``.
-
 Categories must be unique or a ``ValueError`` is raised:
 
 .. ipython:: python
@@ -952,7 +947,6 @@ categorical (categories and ordering). So if you read back the CSV file you have
 relevant columns back to ``category`` and assign the right categories and categories ordering.
 
 .. ipython:: python
-    :okwarning:
 
     import io
 
@@ -969,8 +963,8 @@ relevant columns back to ``category`` and assign the right categories and catego
     df2["cats"]
     # Redo the category
     df2["cats"] = df2["cats"].astype("category")
-    df2["cats"].cat.set_categories(
-        ["very bad", "bad", "medium", "good", "very good"], inplace=True
+    df2["cats"] = df2["cats"].cat.set_categories(
+        ["very bad", "bad", "medium", "good", "very good"]
     )
     df2.dtypes
     df2["cats"]
@@ -1162,16 +1156,12 @@ Constructing a ``Series`` from a ``Categorical`` will not copy the input
 change the original ``Categorical``:
 
 .. ipython:: python
-    :okwarning:
 
     cat = pd.Categorical([1, 2, 3, 10], categories=[1, 2, 3, 4, 10])
     s = pd.Series(cat, name="cat")
     cat
     s.iloc[0:2] = 10
     cat
-    df = pd.DataFrame(s)
-    df["cat"].cat.categories = [1, 2, 3, 4, 5]
-    cat
 
 Use ``copy=True`` to prevent such a behaviour or simply don't reuse ``Categoricals``: