def test_cast_str_to_str(source_stype):
DT = dt.Frame(S=["Right", "middle", None, "", "A" * 1000],
stype=source_stype)
assert DT.stypes == (source_stype, )
RES = DT[:, [dt.str32(f.S), dt.str64(f.S)]]
frame_integrity_check(RES)
assert RES.to_list() == DT.to_list() * 2
def test_cast_bool_to_str():
DT = dt.Frame(P=[False, None, True, True, False, True])
assert DT.stypes == (dt.bool8, )
RES = DT[:, [dt.str32(f.P), dt.str64(f.P)]]
assert RES.stypes == (dt.str32, dt.str64)
ans = ["False", None, "True", "True", "False", "True"]
assert RES.to_list() == [ans, ans]
def test_cast_obj_to_str():
src = [noop, "Hello!", ..., {}, dt, print, None]
DT = dt.Frame(src)
assert DT.stypes == (dt.obj64, )
RES = DT[:, [dt.str32(f[0]), dt.str64(f[0])]]
frame_integrity_check(RES)
ans = [str(x) for x in src]
ans[-1] = None
assert RES.to_list() == [ans, ans]
def test_cast_float_to_str(source_stype):
DT = dt.Frame(J=[3.5, 7.049, -3.18, math.inf, math.nan, 1.0, -math.inf,
1e16, 0],
stype=source_stype)
assert DT.stypes == (source_stype,)
RES = DT[:, [dt.str32(f.J), dt.str64(f.J)]]
frame_integrity_check(RES)
ans = ["3.5", "7.049", "-3.18", "inf", None, "1.0", "-inf", "1.0e+16", "0.0"]
assert RES.to_list() == [ans, ans]
def test_cast_int_to_str(source_stype):
DT = dt.Frame([None, 0, -3, 189, 77, 14, None, 394831, -52939047130424957],
stype=source_stype)
assert DT.stypes == (source_stype, )
RES = DT[:, [dt.str32(f.C0), dt.str64(f.C0)]]
frame_integrity_check(RES)
assert RES.stypes == (dt.str32, dt.str64)
assert RES.shape == (DT.nrows, 2)
ans = [None if v is None else str(v) for v in DT.to_list()[0]]
assert RES.to_list()[0] == ans
def test_cast_int_to_str(stype0):
dt0 = dt.Frame(
[None, 0, -3, 189, 77, 14, None, 394831, -52939047130424957],
stype=stype0)
dt1 = dt0[:, [dt.str32(f.C0), dt.str64(f.C0)]]
dt1.internal.check()
assert dt1.stypes == (dt.str32, dt.str64)
assert dt1.shape == (dt0.nrows, 2)
ans = [None if v is None else str(v) for v in dt0.topython()[0]]
assert dt1.topython()[0] == ans
def test_cast_to_str(src):
def to_str(x):
if x is None: return None
if isinstance(x, bool): return str(int(x))
# if isinstance(x, float) and math.isnan(x): return None
return str(x)
dt0 = dt.Frame(src)
dt1 = dt0[:, [dt.str32(f[i]) for i in range(dt0.ncols)]]
dt2 = dt0[:, [dt.str64(f[i]) for i in range(dt0.ncols)]]
dt1.internal.check()
dt2.internal.check()
assert dt1.stypes == (dt.str32, ) * dt0.ncols
assert dt2.stypes == (dt.str64, ) * dt0.ncols
assert dt1.topython()[0] == [to_str(x) for x in src]
def _write_csv(self, df, file):
# Before writing, we need to convert all columns to strings for two
# reasons:
# - We have to convert any obj64 types to str64: Frame.to_csv can't
# process them.
# - We have to replace None with NULL to tell MySQL, that we have
# actual NULL values. An empty cell is sometimes, but not always a
# NULL value. See #30
# - We have to check if the frame is empty. If so we have to
# circumvent a bug in datatable: see #36
if df.shape[0] == 0:
return None
df = df[:, f[:].remove(f[:]).extend(str64(f[:]))][:, df.names]
df.replace(None, "NULL")
df.to_csv(path=file, header=False)
def transform(self, X: dt.Frame):
logger = None
if self.context and self.context.experiment_id:
logger = make_experiment_logger(
experiment_id=self.context.experiment_id,
tmp_dir=self.context.tmp_dir,
experiment_tmp_dir=self.context.experiment_tmp_dir)
X = dt.Frame(X)
original_zip_column_name = X.names[0]
X = X[:, dt.str64(dt.f[0])]
X.names = ['zip_key']
try:
zip_list = dt.unique(X[~dt.isna(dt.f.zip_key),
0]).to_list()[0] + ['79936']
zip_features = [self.get_zipcode_features(x) for x in zip_list]
X_g = dt.Frame({"zip_key": zip_list})
X_g.cbind(dt.Frame(zip_features))
X_g.key = 'zip_key'
X_result = X[:, :, dt.join(X_g)]
self._output_feature_names = [
"{}:{}.{}".format(self.transformer_name,
original_zip_column_name,
self.replaceBannedCharacters(f))
for f in list(X_result[:, 1:].names)
]
self._feature_desc = [
"Property '{}' of zipcode column ['{}'] from US zipcode database (recipe '{}')"
.format(f, original_zip_column_name, self.transformer_name)
for f in list(X_result[:, 1:].names)
]
return X_result[:, 1:]
except ValueError as ve:
loggerinfo(
logger, "Column '{}' is not a zipcode: {}".format(
original_zip_column_name, str(ve)))
return self.get_zipcode_null_result(X, original_zip_column_name)
except TypeError as te:
loggerwarning(
logger, "Column '{}' triggered TypeError: {}".format(
original_zip_column_name, str(te)))
raise te
