class TestMutate(TestCase):
def setUp(self):
self.df = DataFrame({'Cat': ["A", "A", "A", "B", "B", "B", "B", "C", "C", "C"],
'Date': ["2021-03-01", "2021-03-02", "2021-03-03",
"2021-03-01", "2021-03-02", "2021-03-03", "2021-03-04",
"2021-03-01", "2021-03-02", "2021-03-03"],
'Var1': [10, 14, 13, 22, 28, 23, 30, 6, 8, 9],
'Var2': [250, 245, 209, 360, 328, 359, 372, 74, 78, 80],
'VarNone': [87, 99, None, 120, 128, None, 99, None, None, None],
'VarMixed': [-3, 2, "Null", 0, None, "Null", 5, None, "Null", "Null"],
'VarTextNum': ["5", "8", "-1", "0", "7.4", "11.9", "-8.44", "5", -4.8, 9.2]})
def test_compute_var(self):
compute_var = Mutate(Var3="Var1+Var2")
result = compute_var.apply(self.df)
self.assertEqual([260, 259, 222, 382, 356, 382, 402, 80, 86, 89], result['Var3'])
def test_vars_with_lag(self):
vars_with_lag = Mutate(Var4="Var1-lag_Var1")
result = vars_with_lag.apply(self.df)
self.assertEqual([None, 4, -1, 9, 6, -5, 7, -24, 2, 1], result['Var4'])
def test_leads_with_groups(self):
self.df.add_group('Cat')
leads_with_goups = Mutate(Var5='Var2+lead_Var2')
result = leads_with_goups.apply(self.df)
self.assertEqual([495, 454, None, 688, 687, 731, None, 152, 158, None], result['Var5'])
def apply(self, df):
result = DataFrame()
for var in self.vars:
result.add_column(var, df[var])
kept_group_vars = [var for var in df.groups_vars if var in self.vars]
result = GroupBy(*kept_group_vars).apply(result)
return result
def setUp(self):
self.df = DataFrame({'Dep': ["1", "1", "1", "1", "1", "2", "2", "2", "2", "2"],
'Jour': ["2021-01-01", "2021-01-02", "2021-01-03", "2021-01-04",
"2021-01-05", "2020-11-16", "2020-11-17", "2020-11-18",
"2020-11-19", "2020-11-20"],
'Var': [248, 245, 209, 359, 326, 86, 92, 74, 80, 77],
'VarNone': [87, 99, None, 120, 128, None, 99, None, None, None],
'VarMixed': [-3, 2, "Null", 0, None, "Null", 5, None, "Null", "Null"],
'VarTextNum': ["5", "8", "-1", "0", "7.4", "11.9", "-8.44", "5", -4.8, 9.2]})
def setUp(self):
self.df = DataFrame({'Cat': ["A", "A", "A", "B", "B", "B", "B", "C", "C", "C"],
'Date': ["2021-03-01", "2021-03-02", "2021-03-03",
"2021-03-01", "2021-03-02", "2021-03-03", "2021-03-04",
"2021-03-01", "2021-03-02", "2021-03-03"],
'Var1': [10, 14, 13, 22, 28, 23, 30, 6, 8, 9],
'Var2': [250, 245, 209, 360, 328, 359, 372, 74, 78, 80],
'VarNone': [87, 99, None, 120, 128, None, 99, None, None, None],
'VarMixed': [-3, 2, "Null", 0, None, "Null", 5, None, "Null", "Null"],
'VarTextNum': ["5", "8", "-1", "0", "7.4", "11.9", "-8.44", "5", -4.8, 9.2]})
def setUp(self):
self.df1 = DataFrame({'Reg': ["1", "2", "3", "4", "5", "6", "7", "8", "9", "9"],
'Var1': [10, 14, 13, 22, 28, 23, 30, 6, 8, 9],
'Var2': [250, 245, 209, 360, 328, 359, 372, 74, 78, 80],
'VarNone': [87, 99, None, 120, 128, None, 99, None, None, None],
'VarMixed': [-3, 2, "Null", 0, None, "Null", 5, None, "Null", "Null"],
'VarTextNum': ["5", "8", "-1", "0", "7.4", "11.9", "-8.44", "5", -4.8, 9.2]})
self.df2 = DataFrame({'Region': ["1", "2", "3", "4", "5", "5", "7", "8", "9", "10"],
'Nom': ["A","B","C","D","E","Ebis","G","H","I","J"],
'Var1':[22, 44, 84, 16, 7, 99, 11, 14, 29, 22]})
def setUp(self):
self.df = DataFrame({
'Cat': ["A", "A", "A", "B", "B", "B", "B", "C", "C", "C"],
'Date': [
"2021-03-01", "2021-03-02", "2021-03-03", "2021-03-01",
"2021-03-02", "2021-03-03", "2021-03-04", "2021-03-01",
"2021-03-02", "2021-03-03"
],
'Var1': [10, 14, 13, 22, 28, 23, 30, 6, 8, 9],
'Var2': [250, 245, 209, 360, 328, 359, 372, 74, 78, 80]
})
self.df.add_group('Cat')
def setUp(self):
self.df = DataFrame({
"Cat": ["A", "A", "A", "B", "B", "B", "C", "C"],
"Var1": [348, 402, 397, 380, 589, 520, 620, 289],
"Var2": [74, 81, 85, 71, 102, 99, 101, 76],
"Var3": [74, None, 85, 71, "NaN", 99, 101, 76]
})
class TestUngroup(TestCase):
def setUp(self):
self.df = DataFrame({
'Cat': ["A", "A", "A", "B", "B", "B", "B", "C", "C", "C"],
'Date': [
"2021-03-01", "2021-03-02", "2021-03-03", "2021-03-01",
"2021-03-02", "2021-03-03", "2021-03-04", "2021-03-01",
"2021-03-02", "2021-03-03"
],
'Var1': [10, 14, 13, 22, 28, 23, 30, 6, 8, 9],
'Var2': [250, 245, 209, 360, 328, 359, 372, 74, 78, 80]
})
self.df.add_group('Cat')
def test_ungroup(self):
self.assertEqual([0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
Ungroup().apply(self.df).groups)
def setUp(self):
self.df = DataFrame({'Cat': ["A", "A", "A", "B", "B", "B", "B", "C", "C", "C"],
'Date': ["2021-03-01", "2021-03-02", "2021-03-03",
"2021-03-01", "2021-03-02", "2021-03-03", "2021-03-04",
"2021-03-01", "2021-03-02", "2021-03-03"],
'Var1': [10.1273, 14.26834, 13.9122, 22.74, 28.09, 23.1, 30, 6.06, 8.57, 9.532],
'Var2': [250.1823, 245.682109, 209.0111111111, 360.873421, 328.09534163, 359.07426, 372.07227173, 74, 78, 80],
'VarNone': [87.09912, 99.102, None, 120, 128.88, None, 99.64, None, None, None],
'VarMixed': [-3, 2, "Null", 0, None, "Null", 5, None, "Null", "Null"],
'VarTextNum': ["5", "8", "-1.54", "0.1", "7.4", "11.9", "-8.644", "5", -4.8, 9.2]})
def setUp(self):
self.df = DataFrame({
'X': [
2, 4, 3.5, -3, -1.5, 1, 0.75, -2, -0.5, -3.5, -5, 2.5, 5, -1,
3.5, -1.75, 3, 4, -3.5, -4
],
'Y': [
1, 3, -2.5, 2.5, -3, 5, -0.5, 4, 1, -2.5, -4, -4.5, 0.75, 1.5,
-5, -2.5, 2.5, -2, 2, -1.25
]
})
class TestMovingAverage(TestCase):
def setUp(self):
self.df = DataFrame({'Dep': ["1", "1", "1", "1", "1", "2", "2", "2", "2", "2"],
'Jour': ["2021-01-01", "2021-01-02", "2021-01-03", "2021-01-04",
"2021-01-05", "2020-11-16", "2020-11-17", "2020-11-18",
"2020-11-19", "2020-11-20"],
'Var': [248, 245, 209, 359, 326, 86, 92, 74, 80, 77],
'VarNone': [87, 99, None, 120, 128, None, 99, None, None, None],
'VarMixed': [-3, 2, "Null", 0, None, "Null", 5, None, "Null", "Null"],
'VarTextNum': ["5", "8", "-1", "0", "7.4", "11.9", "-8.44", "5", -4.8, 9.2]})
def test_ungroup_ma(self):
ungroup_ma = MovingAverage(3, 'Jour', 'Var')
result = ungroup_ma.apply(self.df)
self.assertEqual([None, None, 84, 82, 77, 135, 190, 234, 271, 298], result['Var_MA3'])
def test_group_ma(self):
self.df.add_group('Dep')
group_ma = MovingAverage(3, 'Jour', 'Var')
result = group_ma.apply(self.df)
self.assertEqual([None, None, 234, 271, 298, None, None, 84, 82, 77], result['Var_MA3'])
def _operation(self, df):
vars_with_criterion = list(self.__criteria.keys())
if any(var not in df.vars for var in vars_with_criterion):
raise KeyError
result = DataFrame()
for var in df.vars:
result.add_column(var)
for i in range(len(df)):
row_dict = df.row_as_dict(i)
add_row = True
for var in vars_with_criterion:
test_result = False
try:
test_result = eval(
str(var) + " " + str(self.__criteria[var]),
{"__builtins__": {}}, row_dict)
except TypeError:
pass
except Exception as e:
raise e
finally:
if isinstance(test_result, bool):
add_row *= test_result
else:
raise TypeError
if add_row:
result.add_row(df[None, i])
return result
def _operation(self, group_df):
nested_group_list = []
for row in group_df:
nested_group_list.append(row)
index_criteria = []
for var in self.vars:
is_desc = False
if var.startswith("desc_"):
is_desc = True
var = var[5:]
index_criterion = group_df.vars.index(var) + 1
if is_desc:
index_criterion *= -1
index_criteria.append(index_criterion)
default_recursion_limit = getrecursionlimit()
setrecursionlimit(len(group_df) + 10)
sorted_group_list = Sort.__merge_sort(nested_group_list,
index_criteria)
setrecursionlimit(default_recursion_limit)
result = DataFrame()
for var in group_df.vars:
result.add_column(var)
for row in sorted_group_list:
result.add_row(row)
return result
def import_json(path, root=None):
"""
Imports a JSON file as DataFrame.
Parameters
----------
path : str
Absolute or relative path to the JSON file to import
root : str = None
Name of the root's node to import ; if None, imports the first root node of the file
Returns
-------
DataFrame
A DataFrame with the contents of the JSON file
"""
with open(path) as jsonfile:
data = json.load(jsonfile)
roots = list(data.keys())
if len(roots) == 1 or root is None:
root = roots[0]
elif root not in roots:
raise KeyError
table = data[root]
table_vars = list(table[0].keys())
df = DataFrame()
for var in table_vars:
df.add_column(var)
for row in table:
df.add_row(list(row.values()))
return df
def apply(self, df):
result = DataFrame()
groups = df.groups_df
for group_df in groups:
transformed_group = self._operation(group_df)
if len(transformed_group) > 0:
if len(result.vars) == 0:
for var in transformed_group.vars:
result.add_column(var)
for row in transformed_group:
result.add_row(row)
result = GroupBy(*df.groups_vars).apply(result)
return result
def import_csv(path, headers=True, delimiter=";", encoding='ISO-8859-1'):
"""
Imports a CSV file as DataFrame
Parameters
----------
path : str
Absolute or relative path to the CSV file to import
headers : bool = True
Specify if the file have headers
delimiter : str = ";"
Specify the file's delimiter
encoding : str = 'ISO-8859-1'
Specify the file's encoding
Returns
-------
DataFrame
A DataFrame with the contents of the CSV file
"""
df = DataFrame()
with open(path, newline='', encoding=encoding) as csv_file:
reader = csv.reader(csv_file, delimiter=delimiter)
first_row = True
for row in reader:
if first_row:
if headers:
for var in row:
df.add_column(var)
else:
for i in range(len(row)):
name = "Var" + str(i)
df.add_column(name)
first_row = False
else:
df.add_row(row)
return df
def apply(self, df):
result = DataFrame()
other_vars = [
var for var in self.__other.vars
if var not in list(self.__matches.keys())
]
for var in df.vars:
result.add_column(var)
for var in other_vars:
if var in df.vars:
result.add_column("Y_" + str(var))
else:
result.add_column(var)
known_matches = {}
for i in range(len(df)):
base_row = df[None, i]
filter_kw = {}
filter_str = ""
for key in list(self.__matches.keys()):
target_value = df[self.__matches[key], i]
filter_kw[key] = '=="' + str(target_value) + '"'
filter_str += str(key) + "_" + str(target_value)
if known_matches.get(filter_str) is None:
matches = Filter(**filter_kw).apply(self.__other)
if len(matches) == 0:
other_content = [None] * len(other_vars)
else:
other_content = Select(*other_vars).apply(matches)
known_matches[filter_str] = other_content
else:
other_content = known_matches[filter_str]
if isinstance(other_content, DataFrame):
for row in other_content:
new_row = deepcopy(base_row)
new_row.extend(row)
result.add_row(new_row)
else:
new_row = deepcopy(base_row)
new_row.extend(other_content)
result.add_row(new_row)
return result
def apply(self, df):
list_vars = [*df.groups_vars, *self.vars]
df = Select(*list_vars).apply(df)
result = DataFrame()
for var in list_vars:
result.add_column(var)
groups = df.groups_df
for group_df in groups:
row = []
for group_var in df.groups_vars:
row.append(group_df[group_var, 0])
for var in self.vars:
col = group_df[var]
if self.__del_na:
col = [val for val in col if val is not None]
if self.__del_nan:
col = [val for val in col if isinstance(val, Number)]
partial_result = self._operation(col)
if isinstance(partial_result, dict):
keys = list(partial_result.keys())
if (var + "_" + keys[0]) not in result.vars:
last = var
for key in keys:
new_var = var + "_" + key
result.add_column(new_var, after=last)
last = new_var
result.del_column(var)
row.extend(list(partial_result.values()))
else:
row.append(partial_result)
result.add_row(row)
result = GroupBy(*df.groups_vars[:-1]).apply(result)
return result
def setUp(self):
self.df = DataFrame({"Cat": ["A", "A", "A", "A", "B", "B", "B", "B"],
"Var1": [10, 10, 10, 10, 10, 10, 10, 10],
"Var2": [10, 10, 11, 11, 13, 13, 13, 13]})
def test_init_emptyDataFrame(self):
df = DataFrame()
self.assertIsInstance(df, DataFrame)
self.assertEqual(len(df), 0)
self.assertEqual(len(df.vars), 0)
def setUp(self):
self.df = DataFrame({
"Cat": ["A", "A", "A", "B", "B", "B", "C", "C"],
"Var1": [98, 100, 102, 100, 200, 150, 620, 40],
"Var2": [74, 81, 85, 71, 103, 99, 101, 76]
})