Merge remote-tracking branch 'upstream/master' into fix-unsupported-seek-for-httpresponse

Author: mcrot

.travis.yml

@@ -56,7 +56,7 @@ matrix:
     # In allow_failures
     - dist: trusty
       env:
-        - JOB="2.7_SLOW" SLOW=true
+        - JOB="3.6_SLOW" SLOW=true
     # In allow_failures
     - dist: trusty
       env:
@@ -72,7 +72,7 @@ matrix:
     allow_failures:
       - dist: trusty
         env:
-          - JOB="2.7_SLOW" SLOW=true
+          - JOB="3.6_SLOW" SLOW=true
       - dist: trusty
         env:
           - JOB="3.6_NUMPY_DEV" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate"

asv_bench/benchmarks/frame_ctor.py

@@ -16,11 +16,11 @@ class FromDicts(object):
 
     def setup(self):
         N, K = 5000, 50
-        index = tm.makeStringIndex(N)
-        columns = tm.makeStringIndex(K)
-        frame = DataFrame(np.random.randn(N, K), index=index, columns=columns)
+        self.index = tm.makeStringIndex(N)
+        self.columns = tm.makeStringIndex(K)
+        frame = DataFrame(np.random.randn(N, K), index=self.index,
+                          columns=self.columns)
         self.data = frame.to_dict()
-        self.some_dict = list(self.data.values())[0]
         self.dict_list = frame.to_dict(orient='records')
         self.data2 = {i: {j: float(j) for j in range(100)}
                       for i in range(2000)}
@@ -31,8 +31,14 @@ def time_list_of_dict(self):
     def time_nested_dict(self):
         DataFrame(self.data)
 
-    def time_dict(self):
-        Series(self.some_dict)
+    def time_nested_dict_index(self):
+        DataFrame(self.data, index=self.index)
+
+    def time_nested_dict_columns(self):
+        DataFrame(self.data, columns=self.columns)
+
+    def time_nested_dict_index_columns(self):
+        DataFrame(self.data, index=self.index, columns=self.columns)
 
     def time_nested_dict_int64(self):
         # nested dict, integer indexes, regression described in #621

asv_bench/benchmarks/io/csv.py

@@ -118,38 +118,6 @@ def time_read_uint64_na_values(self):
                  na_values=self.na_values)
 
 
-class S3(object):
-    # Make sure that we can read part of a file from S3 without
-    # needing to download the entire thing. Use the timeit.default_timer
-    # to measure wall time instead of CPU time -- we want to see
-    # how long it takes to download the data.
-    timer = timeit.default_timer
-    params = ([None, "gzip", "bz2"], ["python", "c"])
-    param_names = ["compression", "engine"]
-
-    def setup(self, compression, engine):
-        if compression == "bz2" and engine == "c" and PY2:
-            # The Python 2 C parser can't read bz2 from open files.
-            raise NotImplementedError
-        try:
-            import s3fs  # noqa
-        except ImportError:
-            # Skip these benchmarks if `boto` is not installed.
-            raise NotImplementedError
-
-        ext = ""
-        if compression == "gzip":
-            ext = ".gz"
-        elif compression == "bz2":
-            ext = ".bz2"
-        self.big_fname = "s3://pandas-test/large_random.csv" + ext
-
-    def time_read_csv_10_rows(self, compression, engine):
-        # Read a small number of rows from a huge (100,000 x 50) table.
-        read_csv(self.big_fname, nrows=10, compression=compression,
-                 engine=engine)
-
-
 class ReadCSVThousands(BaseIO):
 
     goal_time = 0.2

asv_bench/benchmarks/timeseries.py

@@ -75,8 +75,7 @@ def setup(self):
                                                   freq='S'))
 
     def time_infer_dst(self):
-        with warnings.catch_warnings(record=True):
-            self.index.tz_localize('US/Eastern', infer_dst=True)
+        self.index.tz_localize('US/Eastern', ambiguous='infer')
 
 
 class ResetIndex(object):

ci/build_docs.sh

@@ -24,6 +24,7 @@ if [ "$DOC" ]; then
     source activate pandas
 
     mv "$TRAVIS_BUILD_DIR"/doc /tmp
+    mv "$TRAVIS_BUILD_DIR/LICENSE" /tmp  # included in the docs.
     cd /tmp/doc
 
     echo ###############################

ci/lint.sh

@@ -165,6 +165,14 @@ if [ "$LINT" ]; then
         RET=1
     fi
     echo "Check for deprecated messages without sphinx directive DONE"
+
+    echo "Check for old-style classes"
+    grep -R --include="*.py" -E "class\s\S*[^)]:" pandas scripts
+
+    if [ $? = "0" ]; then
+        RET=1
+    fi
+    echo "Check for old-style classes DONE"
 
 else
     echo "NOT Linting"

ci/requirements-2.7_SLOW.build renamed to ci/requirements-3.6_SLOW.build

@@ -1,5 +1,5 @@
-python=2.7*
+python=3.6*
 python-dateutil
 pytz
-numpy=1.10*
+numpy
 cython

ci/requirements-2.7_SLOW.pip renamed to ci/requirements-3.6_SLOW.pip

@@ -1,7 +1,7 @@
 python-dateutil
 pytz
-numpy=1.10*
-matplotlib=1.4.3
+numpy
+matplotlib
 scipy
 patsy
 xlwt

ci/requirements-2.7_SLOW.run renamed to ci/requirements-3.6_SLOW.run

@@ -2557,6 +2557,8 @@ objects.
    generated/pandas.Index.asi8
    generated/pandas.Index.data
    generated/pandas.Index.flags
+   generated/pandas.Index.holds_integer
+   generated/pandas.Index.is_type_compatible
    generated/pandas.Index.nlevels
    generated/pandas.Index.sort
    generated/pandas.Panel.agg
@@ -2572,4 +2574,5 @@ objects.
    generated/pandas.Series.blocks
    generated/pandas.Series.from_array
    generated/pandas.Series.ix
-   generated/pandas.Timestamp.offset
+   generated/pandas.Series.imag
+   generated/pandas.Series.real

doc/source/_static/print_df_new.png

@@ -397,7 +397,7 @@ In Python, this list would be a list of tuples, so
    pd.DataFrame(a)
 
 For more details and examples see :ref:`the Into to Data Structures
-documentation <basics.dataframe.from_items>`.
+documentation <dsintro>`.
 
 |meltdf|_
 ~~~~~~~~~~~~~~~~