Merge branch 'master' into read-excel-bug-dtype

Author: debnathshoham

.github/workflows/database.yml

@@ -104,7 +104,7 @@ jobs:
       run: python ci/print_skipped.py
 
     - name: Upload coverage to Codecov
-      uses: codecov/codecov-action@v1
+      uses: codecov/codecov-action@v2
       with:
         flags: unittests
         name: codecov-pandas

.github/workflows/posix.yml

@@ -94,7 +94,7 @@ jobs:
       run: python ci/print_skipped.py
 
     - name: Upload coverage to Codecov
-      uses: codecov/codecov-action@v1
+      uses: codecov/codecov-action@v2
       with:
         flags: unittests
         name: codecov-pandas

.github/workflows/python-dev.yml

@@ -78,7 +78,7 @@ jobs:
         coverage report -m
 
     - name: Upload coverage to Codecov
-      uses: codecov/codecov-action@v1
+      uses: codecov/codecov-action@v2
       with:
         flags: unittests
         name: codecov-pandas

.pre-commit-config.yaml

@@ -110,7 +110,7 @@ repos:
         entry: python scripts/generate_pip_deps_from_conda.py
         files: ^(environment.yml|requirements-dev.txt)$
         pass_filenames: false
-        additional_dependencies: [pyyaml]
+        additional_dependencies: [pyyaml, toml]
     -   id: sync-flake8-versions
         name: Check flake8 version is synced across flake8, yesqa, and environment.yml
         language: python

asv_bench/benchmarks/groupby.py

@@ -369,6 +369,18 @@ def time_category_size(self):
         self.draws.groupby(self.cats).size()
 
 
+class Shift:
+    def setup(self):
+        N = 18
+        self.df = DataFrame({"g": ["a", "b"] * 9, "v": list(range(N))})
+
+    def time_defaults(self):
+        self.df.groupby("g").shift()
+
+    def time_fill_value(self):
+        self.df.groupby("g").shift(fill_value=99)
+
+
 class FillNA:
     def setup(self):
         N = 100

asv_bench/benchmarks/reshape.py

@@ -102,6 +102,7 @@ def setup(self, dtype):
         columns = np.arange(n)
         if dtype == "int":
             values = np.arange(m * m * n).reshape(m * m, n)
+            self.df = DataFrame(values, index, columns)
         else:
             # the category branch is ~20x slower than int. So we
             # cut down the size a bit. Now it's only ~3x slower.
@@ -111,7 +112,10 @@ def setup(self, dtype):
             values = np.take(list(string.ascii_letters), indices)
             values = [pd.Categorical(v) for v in values.T]
 
-        self.df = DataFrame(values, index, columns)
+            self.df = DataFrame(
+                {i: cat for i, cat in enumerate(values)}, index, columns
+            )
+
         self.df2 = self.df.iloc[:-1]
 
     def time_full_product(self, dtype):

ci/code_checks.sh

@@ -121,6 +121,9 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
       pandas/io/parsers/ \
       pandas/io/sas/ \
       pandas/io/sql.py \
+      pandas/io/formats/format.py \
+      pandas/io/formats/style.py \
+      pandas/io/stata.py \
       pandas/tseries/
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 

ci/deps/actions-38-locale.yaml

@@ -18,7 +18,7 @@ dependencies:
   - html5lib
   - ipython
   - jinja2
-  - jedi<0.18.0
+  - jedi
   - lxml
   - matplotlib<3.3.0
   - moto

ci/deps/actions-39-slow.yaml

@@ -23,6 +23,7 @@ dependencies:
   - matplotlib
   - moto>=1.3.14
   - flask
+  - numba
   - numexpr
   - numpy
   - openpyxl

ci/deps/actions-39.yaml

@@ -22,6 +22,7 @@ dependencies:
   - matplotlib
   - moto>=1.3.14
   - flask
+  - numba
   - numexpr
   - numpy
   - openpyxl