MAINT: Fix PDF for pandas 3 changes

Fix issues in FRED and FamaFrench

Author: bashtage

ci/azure/azure_template_posix.yml

@@ -16,19 +16,19 @@ jobs:
     vmImage: ${{ parameters.vmImage }}
   strategy:
     matrix:
-      python38_legacy:
-        python.version: '3.8'
-        PANDAS: 1.5.3
       python39_legacy:
         python.version: '3.9'
         PANDAS: 1.5.3
-      python310_recent:
+      python310_legacy:
         python.version: '3.9'
         PANDAS: 2.0.3
       python311_latest:
         python.version: '3.11'
+        PANDAS: 2.1.4
       python312_latest:
         python.version: '3.12'
+      python313_latest:
+        python.version: '3.13'
 
   steps:
   - task: UsePythonVersion@0

ci/azure/azure_template_windows.yml

@@ -16,9 +16,6 @@ jobs:
     vmImage: ${{ parameters.vmImage }}
   strategy:
     matrix:
-      python38_legacy:
-        python.version: '3.8'
-        PANDAS: 1.5.3
       python39_legecy:
         python.version: '3.9'
         PANDAS: 1.5.3
@@ -27,8 +24,11 @@ jobs:
         PANDAS: 2.0.3
       python311_latest:
         python.version: '3.11'
+        PANDAS: 2.1.4
       python312_latest:
         python.version: '3.12'
+      python313_latest:
+        python.version: '3.13'
 
   steps:
   - task: UsePythonVersion@0

pandas_datareader/base.py

@@ -115,8 +115,9 @@ def _read_url_as_StringIO(self, url, params=None):
         if len(text) == 0:
             service = self.__class__.__name__
             raise OSError(
-                "{} request returned no data; check URL for invalid "
-                "inputs: {}".format(service, self.url)
+                "{} request returned no data; check URL for invalid inputs: {}".format(
+                    service, self.url
+                )
             )
         if isinstance(text, bytes):
             out.write(text.decode("utf-8"))

pandas_datareader/data.py

@@ -683,8 +683,7 @@ def DataReader(
 def Options(symbol, data_source=None, session=None):
     if data_source is None:
         warnings.warn(
-            "Options(symbol) is deprecated, use Options(symbol,"
-            " data_source) instead",
+            "Options(symbol) is deprecated, use Options(symbol, data_source) instead",
             FutureWarning,
             stacklevel=2,
         )

pandas_datareader/famafrench.py

@@ -78,8 +78,6 @@ def read(self):
     def _read_one_data(self, url, params):
         params = {
             "index_col": 0,
-            "parse_dates": [0],
-            "date_parser": _parse_date_famafrench,
         }
 
         # headers in these files are not valid
@@ -111,12 +109,14 @@ def _read_one_data(self, url, params):
             start = 0 if not match else match.start()
 
             df = read_csv(StringIO("Date" + src[start:]), **params)
-            try:
-                idx_name = df.index.name  # hack for pandas 0.16.2
-                df = df.to_period(df.index.inferred_freq[:1])
-                df.index.name = idx_name
-            except Exception:
-                pass
+            if df.index.min() > 190000:
+                df.index = to_datetime(df.index.astype(str), format="%Y%m").to_period(
+                    freq="M"
+                )
+            else:
+                df.index = to_datetime(df.index.astype(str), format="%Y").to_period(
+                    freq="Y"
+                )
             df = df.truncate(self.start, self.end)
             datasets[i] = df
 

pandas_datareader/iex/daily.py

@@ -15,7 +15,6 @@
 
 
 class IEXDailyReader(_DailyBaseReader):
-
     """
     Returns DataFrame of historical stock prices
     from symbols, over date range, start to end. To avoid being penalized by

pandas_datareader/moex.py

@@ -197,8 +197,9 @@ def read_all_boards(self):
 
         if len(dfs) == 0:
             raise OSError(
-                "{} returned no data; "
-                "check URL or correct a date".format(self.__class__.__name__)
+                "{} returned no data; check URL or correct a date".format(
+                    self.__class__.__name__
+                )
             )
         elif len(dfs) > 1:
             b = pd.concat(dfs, axis=0, join="outer", sort=True)
@@ -226,8 +227,9 @@ def _read_url_as_String(self, url, params=None):
         if len(text) == 0:
             service = self.__class__.__name__
             raise OSError(
-                "{} request returned no data; check URL for invalid "
-                "inputs: {}".format(service, self.url)
+                "{} request returned no data; check URL for invalid inputs: {}".format(
+                    service, self.url
+                )
             )
         if isinstance(text, bytes):
             text = text.decode("windows-1251")

pandas_datareader/stooq.py

@@ -2,7 +2,6 @@
 
 
 class StooqDailyReader(_DailyBaseReader):
-
     """
     Returns DataFrame/dict of Dataframes of historical stock prices from
     symbols, over date range, start to end.

pandas_datareader/tests/test_famafrench.py

@@ -32,8 +32,8 @@ def test_get_available_datasets(self):
 
     def test_index(self):
         ff = web.DataReader("F-F_Research_Data_Factors", "famafrench")
-        assert ff[0].index.freq == "M"
-        assert ff[1].index.freq == "A-DEC"
+        assert ff[0].index.freq.name == "ME"
+        assert ff[1].index.freq.name == "YE-DEC"
 
     def test_f_f_research(self):
         results = web.DataReader(
@@ -49,49 +49,49 @@ def test_f_f_research(self):
             {
                 "Mkt-RF": [
                     -3.36,
-                    3.40,
+                    3.4,
                     6.31,
-                    2.00,
+                    2.0,
                     -7.89,
                     -5.57,
                     6.93,
                     -4.77,
                     9.54,
                     3.88,
-                    0.60,
+                    0.6,
                     6.82,
                 ],
                 "SMB": [
-                    0.40,
+                    0.4,
                     1.19,
                     1.48,
                     4.87,
                     0.09,
-                    -1.82,
-                    0.20,
-                    -3.00,
+                    -1.81,
+                    0.2,
+                    -3.0,
                     3.96,
-                    1.14,
-                    3.77,
+                    1.13,
+                    3.76,
                     0.73,
                 ],
                 "HML": [
                     0.43,
-                    3.23,
+                    3.22,
                     2.21,
                     2.89,
                     -2.44,
-                    -4.70,
+                    -4.7,
                     -0.31,
-                    -1.90,
+                    -1.9,
                     -3.16,
-                    -2.43,
+                    -2.42,
                     -0.96,
-                    3.70,
+                    3.69,
                 ],
                 "RF": [
-                    0.00,
-                    0.00,
+                    0.0,
+                    0.0,
                     0.01,
                     0.01,
                     0.01,
@@ -114,7 +114,7 @@ def test_f_f_research(self):
 
     def test_me_breakpoints(self):
         results = web.DataReader(
-            "ME_Breakpoints", "famafrench", start="2010-01-01", end="2010-12-01"
+            "ME_Breakpoints", "famafrench", start="2010-01-01", end="2010-12-31"
         )
         assert isinstance(results, dict)
         assert len(results) == 2

pandas_datareader/tests/test_fred.py

@@ -35,13 +35,13 @@ def test_fred_nan(self):
         start = datetime(2010, 1, 1)
         end = datetime(2013, 1, 27)
         df = web.DataReader("DFII5", "fred", start, end)
-        assert pd.isnull(df.loc["2010-01-01"][0])
+        assert pd.isnull(df.loc["2010-01-01"].iloc[0])
 
     def test_fred_parts(self):  # pragma: no cover
         start = datetime(2010, 1, 1)
         end = datetime(2013, 1, 27)
         df = web.get_data_fred("CPIAUCSL", start, end)
-        assert df.loc["2010-05-01"][0] == 217.29
+        assert df.loc["2010-05-01"].iloc[0] == 217.29
 
         t = df.CPIAUCSL.values
         assert np.issubdtype(t.dtype, np.floating)

pandas_datareader/tsp.py

@@ -2,7 +2,6 @@
 
 
 class TSPReader(_BaseReader):
-
     """
     Returns DataFrame of historical TSP fund prices from symbols, over date
     range, start to end.

pandas_datareader/wb.py

@@ -520,7 +520,6 @@
 
 
 class WorldBankReader(_BaseReader):
-
     """
     Download data series from the World Bank's World Development Indicators
 

pandas_datareader/yahoo/headers.py

@@ -1,6 +1,7 @@
 """
 Default header
 """
+
 DEFAULT_HEADERS = {
     "Connection": "keep-alive",
     "Expires": str(-1),

pandas_datareader/yahoo/quotes.py

@@ -14,7 +14,6 @@
 
 
 class YahooQuotesReader(_BaseReader):
-
     """Get current yahoo quote"""
 
     def __init__(

pyproject.toml

@@ -88,7 +88,7 @@ select = ["B","C","E","F","W","T4","B9"]
 
 [tool.black]
 target-version = ["py38", "py39", "py310","py311","py312"]
-required-version = "23.10.1"
+required-version = "25.1.0"
 exclude = """
 (
   pandas_datareader/_version.py

requirements-dev.txt

@@ -1,4 +1,4 @@
-black==23.10.1
+black==25.1.0
 isort>=5.12.0
 flake8-bugbear
 coverage