def test_type_coercion_at_construction(self):
# GH 15682
result = pd.SparseDataFrame(
{
'a': [1, 0, 0],
'b': [0, 1, 0],
'c': [0, 0, 1]
},
dtype='uint8',
default_fill_value=0)
expected = pd.SparseDataFrame(
{
'a': pd.SparseSeries([1, 0, 0], dtype='uint8'),
'b': pd.SparseSeries([0, 1, 0], dtype='uint8'),
'c': pd.SparseSeries([0, 0, 1], dtype='uint8')
},
default_fill_value=0)
tm.assert_sp_frame_equal(result, expected)
def test_is_sparse(check_scipy):
assert com.is_sparse(pd.SparseArray([1, 2, 3]))
assert com.is_sparse(pd.SparseSeries([1, 2, 3]))
assert not com.is_sparse(np.array([1, 2, 3]))
if check_scipy:
import scipy.sparse
assert not com.is_sparse(scipy.sparse.bsr_matrix([1, 2, 3]))
def test_get(self):
s = pd.SparseSeries([1, np.nan, np.nan, 3, np.nan])
self.assertEqual(s.get(0), 1)
assert np.isnan(s.get(1))
assert s.get(5) is None
s = pd.SparseSeries([1, np.nan, 0, 3, 0], index=list('ABCDE'))
self.assertEqual(s.get('A'), 1)
assert np.isnan(s.get('B'))
self.assertEqual(s.get('C'), 0)
assert s.get('XX') is None
s = pd.SparseSeries([1, np.nan, 0, 3, 0], index=list('ABCDE'),
fill_value=0)
self.assertEqual(s.get('A'), 1)
assert np.isnan(s.get('B'))
self.assertEqual(s.get('C'), 0)
assert s.get('XX') is None
def test_concat_sparse_dense(self, kind):
# use first input's fill_value
val1 = np.array([1, 2, np.nan, np.nan, 0, np.nan])
val2 = np.array([3, np.nan, 4, 0, 0])
sparse = pd.SparseSeries(val1, name='x', kind=kind)
dense = pd.Series(val2, name='y')
res = pd.concat([sparse, dense])
exp = pd.SparseSeries(pd.concat([pd.Series(val1), dense]), kind=kind)
tm.assert_sp_series_equal(res, exp)
res = pd.concat([dense, sparse, dense])
exp = pd.concat([dense, pd.Series(val1), dense])
# XXX: changed from SparseSeries to Series[sparse]
exp = pd.Series(
pd.SparseArray(exp, kind=kind),
index=exp.index,
name=exp.name,
)
tm.assert_series_equal(res, exp)
sparse = pd.SparseSeries(val1, name='x', kind=kind, fill_value=0)
dense = pd.Series(val2, name='y')
res = pd.concat([sparse, dense])
# XXX: changed from SparseSeries to Series[sparse]
exp = pd.concat([pd.Series(val1), dense])
exp = pd.Series(
pd.SparseArray(exp, kind=kind, fill_value=0),
index=exp.index,
name=exp.name,
)
tm.assert_series_equal(res, exp)
res = pd.concat([dense, sparse, dense])
exp = pd.concat([dense, pd.Series(val1), dense])
# XXX: changed from SparseSeries to Series[sparse]
exp = pd.Series(
pd.SparseArray(exp, kind=kind, fill_value=0),
index=exp.index,
name=exp.name,
)
tm.assert_series_equal(res, exp)
def test_is_sparse():
assert com.is_sparse(pd.SparseArray([1, 2, 3]))
assert com.is_sparse(pd.SparseSeries([1, 2, 3]))
assert not com.is_sparse(np.array([1, 2, 3]))
# This test will only skip if the previous assertions
# pass AND scipy is not installed.
sparse = pytest.importorskip("scipy.sparse")
assert not com.is_sparse(sparse.bsr_matrix([1, 2, 3]))
def test_get(self):
s = pd.SparseSeries([1, np.nan, np.nan, 3, np.nan])
assert s.get(0) == 1
assert np.isnan(s.get(1))
assert s.get(5) is None
s = pd.SparseSeries([1, np.nan, 0, 3, 0], index=list("ABCDE"))
assert s.get("A") == 1
assert np.isnan(s.get("B"))
assert s.get("C") == 0
assert s.get("XX") is None
s = pd.SparseSeries([1, np.nan, 0, 3, 0],
index=list("ABCDE"),
fill_value=0)
assert s.get("A") == 1
assert np.isnan(s.get("B"))
assert s.get("C") == 0
assert s.get("XX") is None
def test_dataframe_dummies_subset(self, df, sparse):
result = get_dummies(df, prefix=['from_A'], columns=['A'],
sparse=sparse)
expected = DataFrame({'B': ['b', 'b', 'c'],
'C': [1, 2, 3],
'from_A_a': [1, 0, 1],
'from_A_b': [0, 1, 0]}, dtype=np.uint8)
expected[['C']] = df[['C']]
if sparse:
cols = ['from_A_a', 'from_A_b']
expected[cols] = expected[cols].apply(lambda x: pd.SparseSeries(x))
assert_frame_equal(result, expected)
def spoolTestData(self, testData=None):
if not testData is None:
X = testData
else:
X = self.X_test
daily_fingerprint_count, unsupervised, Y = self.spoolData(
X, self.daily_fingerprint_count)
currencies = self.oheC.transform(
np.array(X['currency']).reshape(-1, 1))
for i, col in enumerate(self.oheC.get_feature_names()):
unsupervised[col] = pd.SparseSeries(
currencies[:, i].toarray().ravel(), fill_value=0)
bankEncoded = self.oheB.transform(np.array(X['bank']).reshape(-1, 1))
for i, col in enumerate(self.oheB.get_feature_names()):
unsupervised[col] = pd.SparseSeries(
bankEncoded[:, i].toarray().ravel(), fill_value=0)
return unsupervised, Y
def test_concat_different_fill(self):
val1 = np.array([1, 2, np.nan, np.nan, 0, np.nan])
val2 = np.array([3, np.nan, 4, 0, 0])
for kind in ['integer', 'block']:
sparse1 = pd.SparseSeries(val1, name='x', kind=kind)
sparse2 = pd.SparseSeries(val2, name='y', kind=kind, fill_value=0)
with tm.assert_produces_warning(PerformanceWarning):
res = pd.concat([sparse1, sparse2])
exp = pd.concat([pd.Series(val1), pd.Series(val2)])
exp = pd.SparseSeries(exp, kind=kind)
tm.assert_sp_series_equal(res, exp)
with tm.assert_produces_warning(PerformanceWarning):
res = pd.concat([sparse2, sparse1])
exp = pd.concat([pd.Series(val2), pd.Series(val1)])
exp = pd.SparseSeries(exp, kind=kind, fill_value=0)
tm.assert_sp_series_equal(res, exp)
def test_concat_sparse_dense(self):
# use first input's fill_value
val1 = np.array([1, 2, np.nan, np.nan, 0, np.nan])
val2 = np.array([3, np.nan, 4, 0, 0])
for kind in ['integer', 'block']:
sparse = pd.SparseSeries(val1, name='x', kind=kind)
dense = pd.Series(val2, name='y')
res = pd.concat([sparse, dense])
exp = pd.concat([pd.Series(val1), dense])
exp = pd.SparseSeries(exp, kind=kind)
tm.assert_sp_series_equal(res, exp)
res = pd.concat([dense, sparse, dense])
exp = pd.concat([dense, pd.Series(val1), dense])
exp = pd.SparseSeries(exp, kind=kind)
tm.assert_sp_series_equal(res, exp)
sparse = pd.SparseSeries(val1, name='x', kind=kind, fill_value=0)
dense = pd.Series(val2, name='y')
res = pd.concat([sparse, dense])
exp = pd.concat([pd.Series(val1), dense])
exp = pd.SparseSeries(exp, kind=kind, fill_value=0)
tm.assert_sp_series_equal(res, exp)
res = pd.concat([dense, sparse, dense])
exp = pd.concat([dense, pd.Series(val1), dense])
exp = pd.SparseSeries(exp, kind=kind, fill_value=0)
tm.assert_sp_series_equal(res, exp)
def test_concat_different_fill(self):
val1 = np.array([1, 2, np.nan, np.nan, 0, np.nan])
val2 = np.array([3, np.nan, 4, 0, 0])
for kind in ["integer", "block"]:
sparse1 = pd.SparseSeries(val1, name="x", kind=kind)
sparse2 = pd.SparseSeries(val2, name="y", kind=kind, fill_value=0)
with tm.assert_produces_warning(PerformanceWarning,
raise_on_extra_warnings=False):
res = pd.concat([sparse1, sparse2])
exp = pd.concat([pd.Series(val1), pd.Series(val2)])
exp = pd.SparseSeries(exp, kind=kind)
tm.assert_sp_series_equal(res, exp)
with tm.assert_produces_warning(PerformanceWarning,
raise_on_extra_warnings=False):
res = pd.concat([sparse2, sparse1])
exp = pd.concat([pd.Series(val2), pd.Series(val1)])
exp = pd.SparseSeries(exp, kind=kind, fill_value=0)
tm.assert_sp_series_equal(res, exp)
def transform(self, X, y=None, **transform_params):
links = []
# print(links)
for index, row in X.iteritems():
text = DataCleaner().clean_email(row)
links.append(Links().get_list_keywords(text))
dtm = self.vectorizer.transform(links)
data=self.tfidf_transformer.transform(dtm)
df = pd.SparseDataFrame(data=[pd.SparseSeries(data[i].toarray().ravel())
for i in np.arange(data.shape[0])],
columns=["Lnk."+freq for freq in self.vectorizer.get_feature_names()])
# print("1")
#df=DataFrame(data=data.todense(), columns=list(X.columns.values))
return df
def tests_indexing_with_sparse(self):
# GH 13985
for kind in ['integer', 'block']:
for fill in [True, False, np.nan]:
arr = pd.SparseArray([1, 2, 3], kind=kind)
indexer = pd.SparseArray([True, False, True],
fill_value=fill,
dtype=bool)
tm.assert_sp_array_equal(
pd.SparseArray([1, 3], kind=kind),
arr[indexer],
)
s = pd.SparseSeries(arr,
index=['a', 'b', 'c'],
dtype=np.float64)
exp = pd.SparseSeries([1, 3],
index=['a', 'c'],
dtype=SparseDtype(
np.float64, s.fill_value),
kind=kind)
tm.assert_sp_series_equal(s[indexer], exp)
tm.assert_sp_series_equal(s.loc[indexer], exp)
tm.assert_sp_series_equal(s.iloc[indexer], exp)
indexer = pd.SparseSeries(indexer, index=['a', 'b', 'c'])
tm.assert_sp_series_equal(s[indexer], exp)
tm.assert_sp_series_equal(s.loc[indexer], exp)
msg = ("iLocation based boolean indexing cannot use an "
"indexable as a mask")
with tm.assert_raises_regex(ValueError, msg):
s.iloc[indexer]
def test_dataframe_dummies_drop_first_with_categorical(
self, df, sparse, dtype):
df['cat'] = pd.Categorical(['x', 'y', 'y'])
result = get_dummies(df, drop_first=True, sparse=sparse)
expected = DataFrame({'C': [1, 2, 3],
'A_b': [0, 1, 0],
'B_c': [0, 0, 1],
'cat_y': [0, 1, 1]})
cols = ['A_b', 'B_c', 'cat_y']
expected[cols] = expected[cols].astype(np.uint8)
expected = expected[['C', 'A_b', 'B_c', 'cat_y']]
if sparse:
for col in cols:
expected[col] = pd.SparseSeries(expected[col])
assert_frame_equal(result, expected)
def get_sparse_mx(df, fields, count):
row_ = list(sorted(df[fields[0]].unique()))
col_ = list(sorted(df[fields[1]].unique()))
row = df[fields[0]].astype(pd.api.types.CategoricalDtype(categories=row_)).cat.codes
col = df[fields[1]].astype(pd.api.types.CategoricalDtype(categories=col_)).cat.codes
data = df[count].tolist()
sparse_matrix = sp.csr_matrix((data, (row, col)), shape=(len(row_), len(col_)))
df = pd.SparseDataFrame([pd.SparseSeries(sparse_matrix[i].toarray().ravel(), fill_value=0)
for i in np.arange(sparse_matrix.shape[0])],
index=row_, columns=col_, default_fill_value=0)
return df
def to_pandas(self, sample_field=None, feature_field=None, sparse=None):
'''Get a pandas dataframe of the abundances
Samples are rows, features are columns. Can specify the metadata fields
for the index (default is sample_metadata index) and column labels
(default is feature_metadata index)
Parameters
----------
sample_field : str or None, optional
Name of the sample_metadata column to use for index.
None (default) is the sample_metadata index
feature_field : str or None, optional
Name of the feature_metadata column to use for column names.
None (default) is the feature_metadata index
sparse: bool or None, optional
None (default) to get sparsity based on the underlying Experiment sparsity
True to force to sparse pandas.Dataframe
False to force to standard pandas.Dataframe
Returns
-------
pandas.Dataframe or pandas.SparseDataFrame
'''
if sample_field is None:
ind = self.sample_metadata.index
else:
ind = self.sample_metadata[sample_field]
if feature_field is None:
cols = self.feature_metadata.index
else:
cols = self.feature_metadata[feature_field]
if sparse is not None:
self.sparse = sparse
if self.sparse:
# create list of sparse rows
sr = [
pd.SparseSeries(self.data[i, :].toarray().ravel(),
fill_value=0)
for i in np.arange(self.data.shape[0])
]
df = pd.SparseDataFrame(sr, index=ind, columns=cols)
else:
df = pd.DataFrame(self.data, index=ind, columns=cols, copy=True)
return df
def test_dataframe_dummies_drop_first_with_categorical(
self, df, sparse, dtype):
df["cat"] = pd.Categorical(["x", "y", "y"])
result = get_dummies(df, drop_first=True, sparse=sparse)
expected = DataFrame({
"C": [1, 2, 3],
"A_b": [0, 1, 0],
"B_c": [0, 0, 1],
"cat_y": [0, 1, 1]
})
cols = ["A_b", "B_c", "cat_y"]
expected[cols] = expected[cols].astype(np.uint8)
expected = expected[["C", "A_b", "B_c", "cat_y"]]
if sparse:
for col in cols:
expected[col] = pd.SparseSeries(expected[col])
assert_frame_equal(result, expected)
def sparse_df(connection, sample_ids, feature_ids):
"""
Takes a connection and lists of sample and feature ids and returns a sparse
dataframe.
:param connection:
:param sample_ids:
:param feature_ids:
:return:
"""
dense = df(connection, sample_ids, feature_ids)
sparse_df = dense.to_sparse(fill_value=0.0)
csr = sparse_df.to_coo().tocsr()
sp = pd.SparseDataFrame([
pd.SparseSeries(dense[i].toarray().ravel())
for i in np.arange(dense.shape[0])
])
return sp
def test_sparse_int(self):
# GH 13110
s = pd.SparseSeries([0, 1, 0, 0, 1, 0], fill_value=False)
result = repr(s)
dtype = '' if use_32bit_repr else ', dtype=int32'
exp = ("0 0\n1 1\n2 0\n3 0\n4 1\n"
"5 0\ndtype: int64\nBlockIndex\n"
"Block locations: array([1, 4]{0})\n"
"Block lengths: array([1, 1]{0})".format(dtype))
self.assertEqual(result, exp)
with option_context("display.max_rows", 3):
result = repr(s)
exp = ("0 0\n ..\n5 0\n"
"dtype: int64\nBlockIndex\n"
"Block locations: array([1, 4]{0})\n"
"Block lengths: array([1, 1]{0})".format(dtype))
self.assertEqual(result, exp)
def make_graph_and_calculate_centrality():
# make graph
graph = graph_maker()
# draw the graph if you want to
nx.draw_networkx(graph)
if show_graph:
plt.show()
# get the adjacency matrix
adj_matrix = nx.adjacency_matrix(graph)
# turn it from sparse to regular
sparse_df = pd.SparseDataFrame(
[pd.SparseSeries(adj_matrix[x].toarray().ravel()) for x in np.arange(adj_matrix.shape[0])])
df = sparse_df.to_dense()
# change the name of the rows
df.index = ['Node' + str(x) for x in df]
adj_matrix = df
# make the random walks
random_walks, value_counts, separated_string = make_random_walks(adj_matrix, number_of_walks, length_of_walks)
print "done with random walks"
# Calculate the number of iteration needed
num_of_iteration = calculate_num_of_iteration(number_of_walks, length_of_walks, len(df.index))
# after_parse = wevi_parser(random_walks, window_size)
# print "num of iter is {}".format(num_of_iteration)
# centrality_vector = wevi_automate(after_parse, num_of_iteration)
# centrality_compare(graph, centrality_vector)
if use_new_version:
input1 = str(testing_gensim(separated_string))[1:-1]
else:
print "The input to wevi:"
print wevi_parser(random_walks, window_size)
print "Please paste here the results from wevi"
input1 = raw_input()
compare_dict = centrality_compare(graph, input1, value_counts)
return compare_dict
def test_dataframe_dummies_subset(self, df, sparse):
result = get_dummies(df,
prefix=["from_A"],
columns=["A"],
sparse=sparse)
expected = DataFrame(
{
"B": ["b", "b", "c"],
"C": [1, 2, 3],
"from_A_a": [1, 0, 1],
"from_A_b": [0, 1, 0],
},
dtype=np.uint8,
)
expected[["C"]] = df[["C"]]
if sparse:
cols = ["from_A_a", "from_A_b"]
expected[cols] = expected[cols].apply(lambda x: pd.SparseSeries(x))
assert_frame_equal(result, expected)
def test_is_extension_type(check_scipy):
assert not com.is_extension_type([1, 2, 3])
assert not com.is_extension_type(np.array([1, 2, 3]))
assert not com.is_extension_type(pd.DatetimeIndex([1, 2, 3]))
cat = pd.Categorical([1, 2, 3])
assert com.is_extension_type(cat)
assert com.is_extension_type(pd.Series(cat))
assert com.is_extension_type(pd.SparseArray([1, 2, 3]))
assert com.is_extension_type(pd.SparseSeries([1, 2, 3]))
assert com.is_extension_type(pd.DatetimeIndex([1, 2, 3], tz="US/Eastern"))
dtype = DatetimeTZDtype("ns", tz="US/Eastern")
s = pd.Series([], dtype=dtype)
assert com.is_extension_type(s)
if check_scipy:
import scipy.sparse
assert not com.is_extension_type(scipy.sparse.bsr_matrix([1, 2, 3]))
def test_sparse_bool(self):
# GH 13110
s = pd.SparseSeries([True, False, False, True, False, False],
fill_value=False)
result = repr(s)
dtype = '' if use_32bit_repr else ', dtype=int32'
exp = ("0 True\n1 False\n2 False\n"
"3 True\n4 False\n5 False\n"
"dtype: Sparse[bool, False]\nBlockIndex\n"
"Block locations: array([0, 3]{0})\n"
"Block lengths: array([1, 1]{0})".format(dtype))
assert result == exp
with option_context("display.max_rows", 3):
result = repr(s)
exp = ("0 True\n ... \n5 False\n"
"Length: 6, dtype: Sparse[bool, False]\nBlockIndex\n"
"Block locations: array([0, 3]{0})\n"
"Block lengths: array([1, 1]{0})".format(dtype))
assert result == exp
def test_sparse_int(self):
# GH 13110
s = pd.SparseSeries([0, 1, 0, 0, 1, 0], fill_value=False)
result = repr(s)
dtype = "" if use_32bit_repr else ", dtype=int32"
exp = ("0 0\n1 1\n2 0\n3 0\n4 1\n"
"5 0\ndtype: Sparse[int64, False]\nBlockIndex\n"
"Block locations: array([1, 4]{0})\n"
"Block lengths: array([1, 1]{0})".format(dtype))
assert result == exp
with option_context("display.max_rows", 3, "display.show_dimensions",
False):
result = repr(s)
exp = ("0 0\n ..\n5 0\n"
"dtype: Sparse[int64, False]\nBlockIndex\n"
"Block locations: array([1, 4]{0})\n"
"Block lengths: array([1, 1]{0})".format(dtype))
assert result == exp
def test_is_extension_type():
assert not com.is_extension_type([1, 2, 3])
assert not com.is_extension_type(np.array([1, 2, 3]))
assert not com.is_extension_type(pd.DatetimeIndex([1, 2, 3]))
cat = pd.Categorical([1, 2, 3])
assert com.is_extension_type(cat)
assert com.is_extension_type(pd.Series(cat))
assert com.is_extension_type(pd.SparseArray([1, 2, 3]))
assert com.is_extension_type(pd.SparseSeries([1, 2, 3]))
assert com.is_extension_type(pd.DatetimeIndex([1, 2, 3], tz="US/Eastern"))
dtype = DatetimeTZDtype("ns", tz="US/Eastern")
s = pd.Series([], dtype=dtype)
assert com.is_extension_type(s)
# This test will only skip if the previous assertions
# pass AND scipy is not installed.
sparse = pytest.importorskip("scipy.sparse")
assert not com.is_extension_type(sparse.bsr_matrix([1, 2, 3]))
def sparsity(self):
data = pd.read_csv('data-files/raw_data_march.csv')
data.drop(data.columns[[0, 1, 2, 3, 4, 7, 12, 13, 14, 15, 16, 17, 18, 19]], axis=1, inplace=True)
#df = data.pivot_table(index=['Practitioner'], columns=['ISBN'], values=['Qty'])
#print (df)
user = list(data['Practitioner'].unique())
isbn = list(data['ISBN'].unique())
d = data['Qty'].tolist()
row = data.Practitioner.astype('category', categories=user).cat.codes
col = data.ISBN.astype('category', categories=isbn).cat.codes
sparse_matrix = sps.csr_matrix((d, (row, col)), shape=(len(user), len(isbn)))
dfs=pd.SparseDataFrame([ pd.SparseSeries(sparse_matrix[i].toarray().ravel(), fill_value=0)
for i in np.arange(sparse_matrix.shape[0]) ], index=user, columns=isbn, default_fill_value=0)
#print (dfs)
# calculate sparsity here
print (dfs.density)
# calculation ends
return dfs, data
def test_constructor_preserve_attr(self):
# GH 13866
arr = pd.SparseArray([1, 0, 3, 0], dtype=np.int64, fill_value=0)
assert arr.dtype == np.int64
assert arr.fill_value == 0
df = pd.SparseDataFrame({'x': arr})
assert df['x'].dtype == np.int64
assert df['x'].fill_value == 0
s = pd.SparseSeries(arr, name='x')
assert s.dtype == np.int64
assert s.fill_value == 0
df = pd.SparseDataFrame(s)
assert df['x'].dtype == np.int64
assert df['x'].fill_value == 0
df = pd.SparseDataFrame({'x': s})
assert df['x'].dtype == np.int64
assert df['x'].fill_value == 0
def tfidf(site_dict):
""" Find 10 words with highest TF-IDF for each site """
tfidf = TfidfVectorizer()
tfs = tfidf.fit_transform(site_dict.values())
tfidf_data = pd.DataFrame([
pd.SparseSeries(tfs[i].toarray().ravel())
for i in np.arange(tfs.shape[0])
])
columns = tfidf.get_feature_names()
tfidf_data.columns = columns
tfidf_data.index = site_dict.keys()
tfidf_data = tfidf_data.stack().reset_index()
tfidf_data = tfidf_data.rename(columns={
'level_0': 'site',
'level_1': 'term',
0: 'tfidf'
})
tfidf_data = tfidf_data.sort_values(
by=['site', 'tfidf'], ascending=False).groupby('site').head(10)
return tfidf_data
def test_dataframe_dummies_prefix_dict(self, sparse):
prefixes = {'A': 'from_A', 'B': 'from_B'}
df = DataFrame({'C': [1, 2, 3],
'A': ['a', 'b', 'a'],
'B': ['b', 'b', 'c']})
result = get_dummies(df, prefix=prefixes, sparse=sparse)
expected = DataFrame({'C': [1, 2, 3],
'from_A_a': [1, 0, 1],
'from_A_b': [0, 1, 0],
'from_B_b': [1, 1, 0],
'from_B_c': [0, 0, 1]})
columns = ['from_A_a', 'from_A_b', 'from_B_b', 'from_B_c']
expected[columns] = expected[columns].astype(np.uint8)
if sparse:
expected[columns] = expected[columns].apply(
lambda x: pd.SparseSeries(x)
)
assert_frame_equal(result, expected)
def test_constructor_preserve_attr(self):
# GH 13866
arr = pd.SparseArray([1, 0, 3, 0], dtype=np.int64, fill_value=0)
self.assertEqual(arr.dtype, np.int64)
self.assertEqual(arr.fill_value, 0)
df = pd.SparseDataFrame({'x': arr})
self.assertEqual(df['x'].dtype, np.int64)
self.assertEqual(df['x'].fill_value, 0)
s = pd.SparseSeries(arr, name='x')
self.assertEqual(s.dtype, np.int64)
self.assertEqual(s.fill_value, 0)
df = pd.SparseDataFrame(s)
self.assertEqual(df['x'].dtype, np.int64)
self.assertEqual(df['x'].fill_value, 0)
df = pd.SparseDataFrame({'x': s})
self.assertEqual(df['x'].dtype, np.int64)
self.assertEqual(df['x'].fill_value, 0)