def __init__(self,
df: pd.DataFrame,
mn: str,
un: str,
dim: str = 'col',
digits: int = 5):
"""
Constructor / Initiate the class
Parameters
----------
df : pandas.DataFrame
DataFrame used for analysis
mn : str
string with all the results from the multivariate normality tests
un : str
string with all the results from the univariate normality tests
dim : str
indicate whether one wants to test for normality along the columns 'col' or rows
'row', default is 'col'
digits : int
number of decimal places to round down
"""
super().__init__(dim=dim, digits=digits)
Assertor.evaluate_pd_dataframe(df)
Assertor.evaluate_numeric_df(df)
Assertor.evaluate_data_type({mn: str, un: str, dim: str, digits: int})
self.df = df
self.mn = mn
self.un = un
self.dim = dim
self.digits = digits
def test_access_static_evaluate_pd_data_frame_method(self, invalid_object):
"""
Test that it is possible to access the static evaluate_pd_dataframe() method without
instantiating the Assertor class
"""
with pt.raises(TypeError):
Assertor.evaluate_pd_dataframe(invalid_object)
def __init__(self, df: pd.DataFrame):
"""
Constructor / Initiate the class
Parameters
----------
df : pandas.DataFrame
Dataframe for which one wants to test for normality
"""
Assertor.evaluate_pd_dataframe(df)
Assertor.evaluate_numeric_df(df)
if np.prod(df.shape) < 400:
raise ValueError(
"pd.DataFrame must have at least 400 observations, i.e. (20 x 20) in order to "
"conduct any meaningful normality tests, got {}".format(
df.shape))
self.df = df
def __init__(self, df: pd.DataFrame = None):
"""
Constructor / Initiate the class
Parameters
----------
df : pandas.DataFrame
df to be analysed
"""
if type(self) == NormalityTest:
raise BaseClassCannotBeInstantiated(
"base class '{}' cannot be instantiated".format(
self.__class__.__name__))
Assertor.evaluate_pd_dataframe(df)
r('if (!is.element("MVN", installed.packages()[,1])){ '
'install.packages("MVN", dep = TRUE)}')
self.df = numpy2ri.numpy2ri(np.array(df))
gc.collect()
def __init__(self, df: pd.DataFrame, dim: str = 'col', digits: int = 5):
"""
Constructor / Initiate the class
Parameters
----------
df : pandas.DataFrame
Dataframe for which one wants to generate / test
dim : str
indicate whether one wants to test for normality along the columns 'col' or rows
'row', default is 'col'
digits : int
number of decimal places to round down
"""
super().__init__(dim=dim, digits=digits)
Assertor.evaluate_pd_dataframe(df)
Assertor.evaluate_numeric_df(df)
Assertor.evaluate_data_type({dim: str, digits: int})
self.df = df
self.dim = dim
self.digits = digits
def to_excel(df: pd.DataFrame,
file_dir: str = "reports/xlsx",
header: bool = True,
index: bool = True):
"""
Method that converts dataframe (df) to Excel
Parameters
----------
df : pandas.DataFrame
dataframe to be converted into excel
file_dir: str
directory to save the file
header : bool
Write out the column names
index : bool
Write row names
"""
Assertor.evaluate_pd_dataframe(df)
Assertor.evaluate_data_type({file_dir: str})
local_time = datetime.datetime.now().isoformat().replace(":",
"-").replace(
".", "-")
filepath = os.path.join(file_dir,
"ExcelDataFrame_" + local_time + ".xlsx")
try:
if not os.path.exists(file_dir):
os.makedirs(file_dir)
except Exception as e:
raise OSError("creation of dir " + file_dir + " failed with: " +
str(e))
df.to_excel(filepath, header=header, index=index)