def fillna():
def arg_value():
if _spec.depth == _spec.max_depth:
output: pd.DataFrame = _spec.output
all_values = set([
i for col in output for i in output[col]
if (not pd.isnull(i))
])
yield from map(lambda x: AnnotatedVal(x, cost=2),
Select(all_values))
def arg_limit(v_self: pd.DataFrame):
yield from map(lambda x: AnnotatedVal(x, cost=5),
Select(range(1, (max(v_self.shape) + 1))))
def rarg_limit(v_self: pd.DataFrame):
(nr, nc) = v_self.shape
if coin_flip() == 0:
yield random.choice(range(1, max(nr, 2)))
else:
yield random.choice(range(1, max(nc, 2)))
def rarg_value():
yield random.uniform((-1000), 1000)
_self = RExt(DType(pd.DataFrame), defaultRandDf(nan_prob=0.5))
_limit = Chain(Default(None), RExt(DType(int), rarg_limit(_self)),
arg_limit(_self))
_value = Chain(Default(None), RExt(FType(np.isscalar), rarg_value()),
Ext(DType([dict, pd.Series, pd.DataFrame])),
arg_value())
def diff():
def arg_periods(v_self: pd.DataFrame):
(nr, _) = v_self.shape
yield random.choice(range((-(nr - 1)), nr))
_self = RExt(DType(pd.DataFrame), defaultRandDf(nan_prob=0.1))
_periods = Chain(Default(1), RExt(DType(int), arg_periods(_self)))
def astype():
def arg_astype_partial(v_self):
if _spec.depth == _spec.max_depth:
v_self: pd.DataFrame = v_self
output: pd.DataFrame = _spec.output
try:
if set(output.columns).issubset(set(v_self.columns)):
yield dict(output.dtypes)
except:
pass
def arg_dtype(v_self: pd.DataFrame):
pool = ['int32', 'uint32', 'float64', 'float32', 'int64', 'uint64']
mapping = {
pool[i]: (([None] + pool[:i]) + pool[(i + 1):])
for i in range(len(pool))
}
mapping['object'] = [None]
res = {}
for col in v_self.columns:
chosen = random.choice(mapping[str(v_self.dtypes[col])])
if chosen is not None:
res[col] = chosen
yield res
_self = RExt(DType(pd.DataFrame), defaultRandDf())
_dtype = Chain(RExt(DType(dict), arg_dtype(_self)),
arg_astype_partial(_self))
def add():
def arg_other(v_self: pd.DataFrame):
(nr, nc) = v_self.shape
v_nc = random.choice([nc, nc - 1, nc + 1])
val = next(
defaultRandDf(num_rows=nr,
num_columns=v_nc,
column_levels=v_self.columns.nlevels,
col_prefix='i1_',
value_bags=[*ints_bags, *floats_bags]))
val.index = v_self.index
if (coin_flip() == 0) and (len(val.columns) == nc):
val.columns = v_self.columns
elif v_self.columns.nlevels == 1:
val.columns = pd.Index(
random.sample(
set((list(v_self.columns) + list(val.columns))),
len(val.columns)))
else:
val.columns = pd.MultiIndex.from_tuples(
random.sample(
set((list(v_self.columns) + list(val.columns))),
len(val.columns)))
yield val
def arg_fill_value():
yield random.uniform((-100), 100)
_self = RExt(DType(pd.DataFrame),
defaultRandDf(value_bags=[*ints_bags, *floats_bags]))
_other = RExt(DType(pd.DataFrame), arg_other(_self))
_fill_value = Chain(Default(None), RExt(DType(float),
arg_fill_value()))
def round():
def arg_decimals():
yield random.choice([1, 2, 3, 4, 5])
_self = RExt(DType(pd.DataFrame), defaultRandDf(nan_prob=0.1))
_decimals = Chain(Default(0), RExt(DType(int), arg_decimals()))
def clip():
def arg_lower(v_self: pd.DataFrame):
vals = list(filter((lambda x: (is_int(x) or is_float(x))), list(v_self.values.flatten())))
if len(vals) == 0:
return
yield random.uniform(min(vals), max(vals))
def arg_upper(v_self: pd.DataFrame, v_lower):
vals = list(filter((lambda x: (is_int(x) or is_float(x))), list(v_self.values.flatten())))
if len(vals) == 0:
return
if v_lower is None:
v_lower = min(vals)
yield random.uniform(v_lower, max(vals))
_self = RExt(DType(pd.DataFrame), defaultRandDf(value_bags=[*ints_bags, *floats_bags]))
_lower = Chain(Default(None), RExt(DType(float), arg_lower(_self)))
_upper = Chain(Default(None), RExt(DType(float), arg_upper(_self, _lower)))
def head():
def arg_head_partial(v_self: pd.DataFrame):
if _spec.depth == _spec.max_depth:
output: pd.DataFrame = _spec.output
yield AnnotatedVal(output.shape[0], cost=0)
yield from Select(list(range(1, v_self.shape[0] + 1)))
def arg_n(v_self: pd.DataFrame):
pool = list(set(([5] + list(range(1, len(v_self))))))
yield random.choice(pool)
_self = RExt(DType(pd.DataFrame), defaultRandDf())
_n = Chain(Default(5), RExt(DType(int), arg_n(_self)), arg_head_partial(_self))
def reindex():
def arg_labels(v_self: pd.DataFrame):
(nr, nc) = v_self.shape
if coin_flip() == 0:
vals = list(v_self.index)
new_vals = list(StrColGen(all_distinct=True).generate((nr // 2))[1].values())
yield list(random.sample((vals + new_vals), nr))
else:
vals = list(v_self.columns)
new_vals = list(StrColGen(all_distinct=True).generate((nc // 2))[1].values())
yield list(random.sample((vals + new_vals), nc))
def arg_fill_value():
yield random.uniform((- 100), 100)
_self = RExt(DType(pd.DataFrame), defaultRandDf())
_labels = RExt(DType([list, dict]), arg_labels(_self))
_fill_value = Chain(Default(np.NaN), RExt(DType(float), arg_fill_value()))
