fork/cellxgene
1
0
Fork 0
mirror of https://github.com/chanzuckerberg/cellxgene.git synced 2026-10-02 21:08:12 +08:00
Code Issues Packages Projects Releases Wiki Activity

Apply yapf to python files

Browse Source
This commit is contained in:
Matt Weiden
2019-12-19 15:20:41 -08:00
parent 42a8d45bd7
commit cdca128a01
43 changed files with 1143 additions and 678 deletions
Download Patch File Download Diff File Expand all files Collapse all files
server/app/util/fbs/matrix.py
+25 -15
View File
@@ -25,7 +25,8 @@ def CreateNumpyVector(builder, x):
"""CreateNumpyVector writes a numpy array into the buffer."""
if not isinstance(x, np.ndarray):
raise TypeError(f"non-numpy-ndarray passed to CreateNumpyVector ({type(x)}")
raise TypeError(
f"non-numpy-ndarray passed to CreateNumpyVector ({type(x)}")
if x.dtype.kind not in ['b', 'i', 'u', 'f']:
raise TypeError("numpy-ndarray holds elements of unsupported datatype")
@@ -46,7 +47,8 @@ def CreateNumpyVector(builder, x):
builder.head = int(builder.Head() - len)
# tobytes ensures c_contiguous ordering
builder.Bytes[builder.Head():builder.Head() + len] = x_little_endian.tobytes(order='C')
builder.Bytes[builder.Head():builder.Head() +
len] = x_little_endian.tobytes(order='C')
return builder.EndVector(x.size)
@@ -119,12 +121,10 @@ column_encoding_type_map = {
np.dtype(np.float64).str: (TypedArray.TypedArray.Float32Array, np.float32),
np.dtype(np.float32).str: (TypedArray.TypedArray.Float32Array, np.float32),
np.dtype(np.float16).str: (TypedArray.TypedArray.Float32Array, np.float32),
np.dtype(np.int8).str: (TypedArray.TypedArray.Int32Array, np.int32),
np.dtype(np.int16).str: (TypedArray.TypedArray.Int32Array, np.int32),
np.dtype(np.int32).str: (TypedArray.TypedArray.Int32Array, np.int32),
np.dtype(np.int64).str: (TypedArray.TypedArray.Int32Array, np.int32),
np.dtype(np.uint8).str: (TypedArray.TypedArray.Uint32Array, np.uint32),
np.dtype(np.uint16).str: (TypedArray.TypedArray.Uint32Array, np.uint32),
np.dtype(np.uint32).str: (TypedArray.TypedArray.Uint32Array, np.uint32),
@@ -141,7 +141,6 @@ index_encoding_type_map = {
# array protocol string: ( array_type, as_type )
np.dtype(np.int32).str: (TypedArray.TypedArray.Int32Array, np.int32),
np.dtype(np.int64).str: (TypedArray.TypedArray.Int32Array, np.int32),
np.dtype(np.uint32).str: (TypedArray.TypedArray.Uint32Array, np.uint32),
np.dtype(np.uint64).str: (TypedArray.TypedArray.Uint32Array, np.uint32)
}
@@ -192,7 +191,8 @@ def encode_matrix_fbs(matrix, row_idx=None, col_idx=None):
columns = []
for cidx in range(n_cols - 1, -1, -1):
# serialize the typed array
col = matrix.iloc[:, cidx] if isinstance(matrix, pd.DataFrame) else matrix[:, cidx]
col = matrix.iloc[:, cidx] if isinstance(
matrix, pd.DataFrame) else matrix[:, cidx]
typed_arr = serialize_typed_array(builder, col, column_encoding)
# serialize the Column union
@@ -218,12 +218,18 @@ def encode_matrix_fbs(matrix, row_idx=None, col_idx=None):
def deserialize_typed_array(tarr):
type_map = {
TypedArray.TypedArray.NONE: None,
TypedArray.TypedArray.Uint32Array: Uint32Array.Uint32Array,
TypedArray.TypedArray.Int32Array: Int32Array.Int32Array,
TypedArray.TypedArray.Float32Array: Float32Array.Float32Array,
TypedArray.TypedArray.Float64Array: Float64Array.Float64Array,
TypedArray.TypedArray.JSONEncodedArray: JSONEncodedArray.JSONEncodedArray
TypedArray.TypedArray.NONE:
None,
TypedArray.TypedArray.Uint32Array:
Uint32Array.Uint32Array,
TypedArray.TypedArray.Int32Array:
Int32Array.Int32Array,
TypedArray.TypedArray.Float32Array:
Float32Array.Float32Array,
TypedArray.TypedArray.Float64Array:
Float64Array.Float64Array,
TypedArray.TypedArray.JSONEncodedArray:
JSONEncodedArray.JSONEncodedArray
}
(u_type, u) = tarr
if u_type is TypedArray.TypedArray.NONE:
@@ -257,13 +263,16 @@ def decode_matrix_fbs(fbs):
columns_length = matrix.ColumnsLength()
columns_index = deserialize_typed_array((matrix.ColIndexType(), matrix.ColIndex()))
columns_index = deserialize_typed_array(
(matrix.ColIndexType(), matrix.ColIndex()))
if columns_index is None:
columns_index = range(0, n_cols)
# sanity checks
if len(columns_index) != n_cols or columns_length != n_cols:
raise ValueError("FBS column count does not match number of columns in underlying matrix")
raise ValueError(
"FBS column count does not match number of columns in underlying matrix"
)
columns_data = {}
columns_type = {}
@@ -277,7 +286,8 @@ def decode_matrix_fbs(fbs):
if col.UType() is TypedArray.TypedArray.JSONEncodedArray:
columns_type[columns_index[col_idx]] = "category"
df = pd.DataFrame.from_dict(data=columns_data).astype(columns_type, copy=False)
df = pd.DataFrame.from_dict(data=columns_data).astype(columns_type,
copy=False)
# more sanity checks
if not df.columns.is_unique or len(df.columns) != n_cols: