def scaling(self):
while(1):
print("\nTasks (Feature Scaling)")
for task in self.tasks:
print(task)
while(1):
try:
choice = int(input(("\n\nWhat you want to do? (Press -1 to go back) ")))
except ValueError:
print("Integer Value required. Try again.....")
continue
break
if choice == -1:
break
elif choice == 1:
self.normalization()
elif choice == 2:
self.standardization()
elif choice==3:
DataDescription.showDataset(self)
else:
print("\nWrong Integer value!! Try again..")
# Returns all the changes on the DataFrame.
return self.data
def categoricalMain(self):
while(1):
print("\nTasks")
for task in self.tasks:
print(task)
while(1):
try:
choice = int(input(("\n\nWhat you want to do? (Press -1 to go back) ")))
except ValueError:
print("Integer Value required. Try again...")
continue
break
if choice == -1:
break
elif choice == 1:
self.categoricalColumn()
elif choice == 2:
self.categoricalColumn()
self.encoding()
elif choice == 3:
DataDescription.showDataset(self)
else:
print("\nWrong Integer value!! Try again..")
# return the data after modifying
return self.data
def normalization(self):
while(1):
print("\nTasks (Normalization)")
for task in self.tasks_normalization:
print(task)
while(1):
try:
choice = int(input(("\n\nWhat you want to do? (Press -1 to go back) ")))
except ValueError:
print("Integer Value required. Try again.....")
continue
break
if choice == -1:
break
# Performs normalization on the columns provided.
elif choice == 1:
print(self.data.dtypes)
columns = input("Enter all the column" + "(s)" + "you want to normalize (Press -1 to go back) ").lower()
if columns == "-1":
break
for column in columns.split(" "):
# This is the basic approach to perform MinMax Scaler on a set of data.
try:
minValue = self.data[column].min()
maxValue = self.data[column].max()
self.data[column] = (self.data[column] - minValue)/(maxValue - minValue)
except:
print("\nNot possible....")
print("Done....")
# Performs normalization on whole dataset.
elif choice == 2:
try:
self.data = pd.DataFrame(MinMaxScaler().fit_transform(self.data))
print("Done.......")
except:
print("\nString Columns are present. So, " + "NOT" + " possible.\nYou can try the first option though.")
elif choice==3:
DataDescription.showDataset(self)
else:
print("\nYou pressed the wrong key!! Try again..")
return
def standardization(self):
while (1):
print("\nTasks (Standardization)")
for task in self.tasks_standardization:
print(task)
while (1):
try:
choice = int(
input(
("\n\nWhat you want to do? [enter -1 to go back] "
)))
except ValueError:
print("Integer Value required. Try again.....")
continue
break
if choice == -1:
break
elif choice == 1:
print(self.data.dtypes)
columns = input(
"Enter all the column" + self.bold_text_start + "(s)" +
self.bold_text_end +
"you want to normalize [enter -1 to go back] ").lower()
if columns == "-1":
break
for column in columns.split(" "):
try:
mean = self.data[column].mean()
standard_deviation = self.data[column].std()
self.data[column] = (self.data[column] -
mean) / (standard_deviation)
except:
print("\nNot possible....")
print("Done....")
elif choice == 2:
try:
self.data = pd.DataFrame(StandardScaler().fit_transform(
self.data))
print("Done.......")
except:
print("\nString Columns are present. So, " +
self.bold_text_start + "NOT" + self.bold_text_end +
" possible. \nYou can try the first option though.")
break
elif choice == 3:
DataDescription.showDataset(self)
else:
print("\nWrong choice!! Try again...")
return
def preprocessorMain(self):
self.removeTargetColumn()
while (1):
print("\nTasks (Preprocessing)\n")
for task in self.tasks:
print(task)
while (1):
try:
choice = int(
input(
"\nWhat do you want to do? [enter -1 to exit]: "))
except ValueError:
print("Integer Value required. Try again.....")
continue
break
if choice == -1:
exit()
elif choice == 1:
DataDescription(self.data).describe()
elif choice == 2:
self.data = Imputation(self.data).imputer()
elif choice == 3:
self.data = Categorical(self.data).categoricalMain()
elif choice == 4:
self.data = FeatureScaling(self.data).scaling()
elif choice == 5:
Download(self.data).download()
else:
print("\nWrong choice!! Try again...")
def imputer(self):
while (1):
print("\nImputation Tasks")
for task in self.tasks:
print(task)
while (1):
try:
choice = int(
input((
"\nWhat you want to do? (Press -1 to go back) ")))
except ValueError:
print("Integer Value required. Try again.....")
continue
break
if choice == -1:
break
elif choice == 1:
self.printNullValues()
elif choice == 2:
self.removeColumn()
elif choice == 3:
self.fillNullWithMean()
elif choice == 4:
self.fillNullWithMedian()
elif choice == 5:
self.fillNullWithMode()
elif choice == 6:
DataDescription.showDataset(self)
else:
print("\nWrong Integer value!! Try again..")
return self.data
def main():
print('-'*10+'Welcome to ML Preprocessor CLI'+'-'*10+'\n\n')
try:
file_path=sys.argv[1]
if file_path.endswith('.csv')==False:
raise IncorrectFileFormatError("file is not in CSV format")
revised_df=readCSV(file_path)
print('\nScreenshot of independent dataframe:\n')
print(revised_df.head())
print('\n'+'-'*30+'\n')
while True:
print('\nTasks(Preprocessing)')
print('1.Data Description')
print('2.Handling NULL values')
print('3.Encoding Categorical Data')
print('4.Feature Scaling of the Dataset')
print('5.Download the modified Dataset\n')
option=int(input('What do you want to do?(Press -1 to exit):'))
if option==-1:
raise ExitError
elif option==1:
data_desc=DataDescription(revised_df)
while True:
option=data_desc.getOption()
if option==-1:
break
elif option==1:
data_desc.showProperty()
elif option==2:
data_desc.showStats()
elif option==3:
data_desc.showDF()
else:
print('Incorrect option!Try again.')
elif option==2:
impute=Imputation(revised_df)
while True:
option=impute.getOption()
if option==-1:
break
elif option==1:
impute.countNULL()
elif option==2:
revised_df=impute.dropColumn()
elif option==3:
revised_df=impute.fillUtil()
elif option==4:
impute.showDF()
else:
print('Incorrect option!Try again.')
elif option==3:
encode=EncodeCategorical(revised_df)
while True:
option=encode.getOption()
if option==-1:
break
elif option==1:
encode.showCategorical()
elif option==2:
revised_df=encode.performOneHotEncodingUtil()
elif option==3:
encode.showDF()
else:
print('Incorrect option!Try again.')
elif option==4:
while True:
scale=FeatureScaling(revised_df)
option=scale.getOption()
if option==-1:
break
elif option==1:
scale.normalizeUtil()
elif option==2:
scale.standardizeUtil()
elif option==3:
scale.showDF()
else:
print('Incorrect option!Try again.')
elif option==5:
download=Download(revised_df)
download.downloadDataframe()
else:
print('Incorrect option!Try again.')
except IndexError as e:
print('File path missing.',e)
except IncorrectFileFormatError as e:
print('Incorrect file format.',e)
except FileNotFoundError as e:
print('File Not Found!',e)
except ExitError as e:
print(e)
except Exception as e:
print('Incorrect option chosen.',e)