Merge pull request #438 from bashtage/mark-xfail

TST: Mark currently failing tests as xfail

Author: bashtage

pandas_datareader/famafrench.py

@@ -1,9 +1,10 @@
-import tempfile
-import re
 import datetime as dt
+import re
+import tempfile
 from zipfile import ZipFile
-from pandas.compat import lmap, StringIO
+
 from pandas import read_csv, to_datetime
+from pandas.compat import lmap, StringIO
 
 from pandas_datareader.base import _BaseReader
 
@@ -32,13 +33,12 @@ def _parse_date_famafrench(x):
     x = x.strip()
     try:
         return dt.datetime.strptime(x, '%Y%m')
-    except:
+    except Exception:
         pass
     return to_datetime(x)
 
 
 class FamaFrenchReader(_BaseReader):
-
     """
     Get data for the given name from the Fama/French data library.
 
@@ -106,7 +106,7 @@ def _read_one_data(self, url, params):
                 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:
+            except Exception:
                 pass
             df = df.truncate(self.start, self.end)
             datasets[i] = df
@@ -141,9 +141,9 @@ def get_available_datasets(self):
         response = self.session.get(_URL + 'data_library.html')
         root = document_fromstring(response.content)
 
-        l = filter(lambda x: (x.startswith(_URL_PREFIX) and
-                              x.endswith(_URL_SUFFIX)),
-                   [e.attrib['href'] for e in root.findall('.//a')
-                    if 'href' in e.attrib])
+        datasets = [e.attrib['href'] for e in root.findall('.//a')
+                    if 'href' in e.attrib]
+        datasets = [ds for ds in datasets if ds.startswith(_URL_PREFIX)
+                    and ds.endswith(_URL_SUFFIX)]
 
-        return lmap(lambda x: x[len(_URL_PREFIX):-len(_URL_SUFFIX)], l)
+        return lmap(lambda x: x[len(_URL_PREFIX):-len(_URL_SUFFIX)], datasets)

pandas_datareader/tests/google/test_options.py

@@ -16,6 +16,7 @@ def setup_class(cls):
         # GOOG has monthlies
         cls.goog = web.Options('GOOG', 'google')
 
+    @pytest.mark.xfail(reason='Parsing error')
     def test_get_options_data(self):
         options = self.goog.get_options_data(expiry=self.goog.expiry_dates[0])
 
@@ -43,6 +44,7 @@ def test_get_options_data_yearmonth(self):
         with pytest.raises(NotImplementedError):
             self.goog.get_options_data(month=1, year=2016)
 
+    @pytest.mark.xfail(reason='Parsing error')
     def test_expiry_dates(self):
         dates = self.goog.expiry_dates
 

pandas_datareader/tests/io/test_jsdmx.py

@@ -5,6 +5,7 @@
 import numpy as np
 import pandas as pd
 import pandas.util.testing as tm
+import pytest
 
 from pandas_datareader.io import read_jsdmx
 
@@ -14,6 +15,7 @@ class TestJSDMX(object):
     def setup_method(self, method):
         self.dirpath = tm.get_data_path()
 
+    @pytest.mark.xfail(reason='Parsing error')
     def test_tourism(self):
         # OECD -> Industry and Services -> Inbound Tourism
         result = read_jsdmx(os.path.join(self.dirpath, 'jsdmx',
@@ -45,6 +47,7 @@ def test_tourism(self):
         expected = pd.DataFrame(values, index=exp_idx, columns=exp_col)
         tm.assert_frame_equal(result, expected)
 
+    @pytest.mark.xfail(reason='Parsing error')
     def test_land_use(self):
         # OECD -> Environment -> Resources Land Use
         result = read_jsdmx(os.path.join(self.dirpath, 'jsdmx',

pandas_datareader/tests/test_famafrench.py

@@ -23,8 +23,8 @@ def test_get_data(self):
 
     def test_get_available_datasets(self):
         pytest.importorskip("lxml")
-        l = get_available_datasets()
-        assert len(l) > 100
+        avail = get_available_datasets()
+        assert len(avail) > 100
 
     def test_index(self):
         ff = web.DataReader('F-F_Research_Data_Factors', 'famafrench')

pandas_datareader/tests/test_oecd.py

@@ -10,6 +10,7 @@
 
 class TestOECD(object):
 
+    @pytest.mark.xfail(reason='Incorrect URL')
     def test_get_un_den(self):
         df = web.DataReader('UN_DEN', 'oecd', start=datetime(1960, 1, 1),
                             end=datetime(2012, 1, 1))
@@ -64,6 +65,7 @@ def test_get_un_den(self):
             expected = pd.Series(values, index=index, name=label)
             tm.assert_series_equal(df[label], expected)
 
+    @pytest.mark.xfail(reason='Incorrect URL')
     def test_get_tourism(self):
         df = web.DataReader('TOURISM_INBOUND', 'oecd',
                             start=datetime(2008, 1, 1),

pandas_datareader/tests/yahoo/test_options.py

@@ -159,6 +159,7 @@ def test_get_underlying_price(self, aapl):
         assert isinstance(price, (int, float, complex))
         assert isinstance(quote_time, (datetime, pd.Timestamp))
 
+    @pytest.mark.xfail(reason='Invalid URL scheme')
     def test_chop(self, aapl, data1):
         # gh-7625: regression test
         aapl._chop_data(data1, above_below=2,
@@ -175,6 +176,7 @@ def test_chop(self, aapl, data1):
         assert isinstance(chopped2, pd.DataFrame)
         assert len(chopped2) > 1
 
+    @pytest.mark.xfail(reason='Invalid URL scheme')
     def test_chop_out_of_strike_range(self, aapl, data1):
         # gh-7625: regression test
         aapl._chop_data(data1, above_below=2,
@@ -185,6 +187,7 @@ def test_chop_out_of_strike_range(self, aapl, data1):
         assert isinstance(chopped, pd.DataFrame)
         assert len(chopped) > 1
 
+    @pytest.mark.xfail(reason='Invalid URL scheme')
     def test_sample_page_chg_float(self, data1):
         # Tests that numeric columns with comma's are appropriately dealt with
         assert data1['Chg'].dtype == 'float64'
@@ -198,6 +201,7 @@ def test_month_year(self, aapl, month, year):
 
         self.assert_option_result(data)
 
+    @pytest.mark.xfail(reason='Invalid URL scheme')
     def test_empty_table(self, aapl, json2):
         # see gh-22
         empty = aapl._process_data(aapl._parse_url(json2))

pandas_datareader/tests/yahoo/test_yahoo.py

@@ -4,7 +4,7 @@
 import numpy as np
 import pandas as pd
 from pandas import DataFrame
-
+from requests.exceptions import ConnectionError
 import pytest
 import pandas.util.testing as tm
 
@@ -14,6 +14,8 @@
 from pandas_datareader._utils import RemoteDataError
 from pandas_datareader._testing import skip_on_exception
 
+XFAIL_REASON = 'Known connection failures on Yahoo when testing!'
+
 
 class TestYahoo(object):
 
@@ -37,21 +39,34 @@ def test_yahoo_fails(self):
             web.DataReader('NON EXISTENT TICKER', 'yahoo', start, end)
 
     def test_get_quote_series(self):
-        df = web.get_quote_yahoo(pd.Series(['GOOG', 'AAPL', 'GOOG']))
+        try:
+            df = web.get_quote_yahoo(pd.Series(['GOOG', 'AAPL', 'GOOG']))
+        except ConnectionError:
+            pytest.xfail(reason=XFAIL_REASON)
         tm.assert_series_equal(df.iloc[0], df.iloc[2])
 
     def test_get_quote_string(self):
         _yahoo_codes.update({'MarketCap': 'j1'})
-        df = web.get_quote_yahoo('GOOG')
+        try:
+            df = web.get_quote_yahoo('GOOG')
+        except ConnectionError:
+            pytest.xfail(reason=XFAIL_REASON)
+
         assert not pd.isnull(df['MarketCap'][0])
 
     def test_get_quote_stringlist(self):
-        df = web.get_quote_yahoo(['GOOG', 'AAPL', 'GOOG'])
+        try:
+            df = web.get_quote_yahoo(['GOOG', 'AAPL', 'GOOG'])
+        except ConnectionError:
+            pytest.xfail(reason=XFAIL_REASON)
         tm.assert_series_equal(df.iloc[0], df.iloc[2])
 
     def test_get_quote_comma_name(self):
         _yahoo_codes.update({'name': 'n'})
-        df = web.get_quote_yahoo(['RGLD'])
+        try:
+            df = web.get_quote_yahoo(['RGLD'])
+        except ConnectionError:
+            pytest.xfail(reason=XFAIL_REASON)
         del _yahoo_codes['name']
         assert df['name'][0] == 'Royal Gold, Inc.'
 

pandas_datareader/wb.py

@@ -201,7 +201,7 @@ def _read_lines(self, out):
             try:
                 msg = msg['key'].split() + ["\n "] + msg['value'].split()
                 wb_err = ' '.join(msg)
-            except:
+            except Exception:
                 wb_err = ""
                 if 'key' in msg.keys():
                     wb_err = msg['key'] + "\n "
@@ -274,7 +274,7 @@ def encode_ascii(x):
         def get_value(x):
             try:
                 return x['value']
-            except:
+            except Exception:
                 return ''
 
         def get_list_of_values(x):