Merge remote-tracking branch 'upstream/master' into depr-converter

Author: TomAugspurger

.gitignore

@@ -106,4 +106,3 @@ doc/build/html/index.html
 doc/tmp.sv
 doc/source/styled.xlsx
 doc/source/templates/
-doc/source/savefig/

asv_bench/benchmarks/frame_ctor.py

@@ -132,7 +132,7 @@ def setup(self, offset, n_steps):
         offset = getattr(offsets, offset)
         self.idx = get_index_for_offset(offset(n_steps, **kwargs))
         self.df = DataFrame(np.random.randn(len(self.idx), 10), index=self.idx)
-        self.d = dict([(col, self.df[col]) for col in self.df.columns])
+        self.d = dict(self.df.items())
 
     def time_frame_ctor(self, offset, n_steps):
         DataFrame(self.d)

asv_bench/benchmarks/io_bench.py

@@ -202,7 +202,7 @@ class read_json_lines(object):
     def setup(self):
         self.N = 100000
         self.C = 5
-        self.df = DataFrame(dict([('float{0}'.format(i), randn(self.N)) for i in range(self.C)]))
+        self.df = DataFrame({('float{0}'.format(i), randn(self.N)) for i in range(self.C)})
         self.df.to_json(self.fname,orient="records",lines=True)
 
     def teardown(self):

asv_bench/benchmarks/packers.py

@@ -17,7 +17,7 @@ def _setup(self):
         self.N = 100000
         self.C = 5
         self.index = date_range('20000101', periods=self.N, freq='H')
-        self.df = DataFrame(dict([('float{0}'.format(i), randn(self.N)) for i in range(self.C)]), index=self.index)
+        self.df = DataFrame(dict(('float{0}'.format(i), randn(self.N)) for i in range(self.C)), index=self.index)
         self.df2 = self.df.copy()
         self.df2['object'] = [('%08x' % randrange((16 ** 8))) for _ in range(self.N)]
         self.remove(self.f)

asv_bench/benchmarks/plotting.py

@@ -10,22 +10,47 @@ def date_range(start=None, end=None, periods=None, freq=None):
     from pandas.tools.plotting import andrews_curves
 
 
+class Plotting(object):
+    goal_time = 0.2
+
+    def setup(self):
+        import matplotlib
+        matplotlib.use('Agg')
+        self.s = Series(np.random.randn(1000000))
+        self.df = DataFrame({'col': self.s})
+
+    def time_series_plot(self):
+        self.s.plot()
+
+    def time_frame_plot(self):
+        self.df.plot()
+
+
 class TimeseriesPlotting(object):
     goal_time = 0.2
 
     def setup(self):
         import matplotlib
         matplotlib.use('Agg')
-        self.N = 2000
-        self.M = 5
-        self.df = DataFrame(np.random.randn(self.N, self.M), index=date_range('1/1/1975', periods=self.N))
+        N = 2000
+        M = 5
+        idx = date_range('1/1/1975', periods=N)
+        self.df = DataFrame(np.random.randn(N, M), index=idx)
+
+        idx_irregular = pd.DatetimeIndex(np.concatenate((idx.values[0:10],
+                                                         idx.values[12:])))
+        self.df2 = DataFrame(np.random.randn(len(idx_irregular), M),
+                             index=idx_irregular)
 
     def time_plot_regular(self):
         self.df.plot()
 
     def time_plot_regular_compat(self):
         self.df.plot(x_compat=True)
 
+    def time_plot_irregular(self):
+        self.df2.plot()
+
 
 class Misc(object):
     goal_time = 0.6

asv_bench/vbench_to_asv.py

@@ -69,7 +69,7 @@ def visit_ClassDef(self, node):
         return node
 
     def visit_TryExcept(self, node):
-        if any([isinstance(x, (ast.Import, ast.ImportFrom)) for x in node.body]):
+        if any(isinstance(x, (ast.Import, ast.ImportFrom)) for x in node.body):
             self.imports.append(node)
         else:
             self.generic_visit(node)

ci/lint.sh

@@ -72,12 +72,31 @@ if [ "$LINT" ]; then
     echo "Linting *.c and *.h DONE"
 
     echo "Check for invalid testing"
-    grep -r -E --include '*.py' --exclude testing.py '(numpy|np)\.testing' pandas
+
+    # Check for the following code in testing:
+    #
+    # np.testing
+    # np.array_equal
+    grep -r -E --include '*.py' --exclude testing.py '(numpy|np)(\.testing|\.array_equal)' pandas/tests/
+
     if [ $? = "0" ]; then
         RET=1
     fi
     echo "Check for invalid testing DONE"
 
+    echo "Check for use of lists instead of generators in built-in Python functions"
+
+    # Example: Avoid `any([i for i in some_iterator])` in favor of `any(i for i in some_iterator)`
+    #
+    # Check the following functions:
+    # any(), all(), sum(), max(), min(), list(), dict(), set(), frozenset(), tuple(), str.join()
+    grep -R --include="*.py*" -E "[^_](any|all|sum|max|min|list|dict|set|frozenset|tuple|join)\(\[.* for .* in .*\]\)"
+
+    if [ $? = "0" ]; then
+        RET=1
+    fi
+    echo "Check for use of lists instead of generators in built-in Python functions DONE"
+
 else
     echo "NOT Linting"
 fi

ci/requirements-3.6.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+source activate pandas
+
+echo "[install 3.6 downstream deps]"
+
+conda install -n pandas -c conda-forge pandas-datareader xarray geopandas seaborn statsmodels scikit-learn dask

ci/requirements-3.6_NUMPY_DEV.build.sh

@@ -12,7 +12,8 @@ PRE_WHEELS="https://7933911d6844c6c53a7d-47bd50c35cd79bd838daf386af554a83.ssl.cf
 pip install --pre --upgrade --timeout=60 -f $PRE_WHEELS numpy scipy
 
 # install dateutil from master
-pip install -U git+git://github.com/dateutil/dateutil.git
+# pip install -U git+git://github.com/dateutil/dateutil.git
+pip install dateutil
 
 # cython via pip
 pip install cython

ci/script_multi.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/bin/bash -e
 
 echo "[script multi]"