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 get(argsfscale):
print("Feature Scaling...")
args_list = argsfscale.split(",")
fsn = args_list[0]
filename = args_list[1]
jfilename = args_list[2]
json_path = currentDirPath + "/jsonfiles/" + jfilename
file_path = currentDirPath + "/csvfiles/" + filename
data = pd.read_csv(file_path)
data_afs = FeatureScaling.Scaling(data, fsn)
data_afs.reset_index(inplace=True, drop=True)
data_afs.to_csv(file_path, index=False)
data_t10 = data_afs.head(10)
data_noff = len(data_afs.columns)
with open(json_path) as jcon:
jdata = json.load(jcon)
jdata.update({'FeatureScaling': fsn})
with open(json_path, 'w') as j_con:
json.dump(jdata, j_con)
return {
'predata': data_t10.to_json(orient='table'),
'fileName': filename,
'numofcol': data_noff,
'jfilename': jfilename
}
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from feature_scaling import FeatureScaling
if __name__ == "__main__":
fc = FeatureScaling()
train_data, test_data = fc.getFeaturedDataframe()
x_train, x_test, Y_train, Y_test = train_test_split(
train_data,
test_data,
random_state=2,
test_size=0.10,
)
reg = LinearRegression()
reg.fit(x_train, Y_train)
print(reg.score(x_test, Y_test))
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)
class Preprocessor:
# The Task associated with this class. This is also the main class of the project.
tasks = [
'1. Data Description', '2. Handling NULL Values',
'3. Encoding Categorical Data', '4. Feature Scaling of the Dataset',
'5. Download the modified dataset'
]
data = 0
def __init__(self):
self.data = DataInput().inputFunction()
print("\n\n" +
"WELCOME TO THE MACHINE LEARNING PREPROCESSOR CLI!!!\n" + "\n\n")
# function to remove the target column of the DataFrame.
def removeTargetColumn(self):
print("Columns\n")
for column in self.data.columns.values:
print(column, end=" ")
while (1):
column = input(
"\nWhich is the target variable:(Press -1 to exit) ").lower()
if column == "-1":
exit()
choice = input("Are you sure?(y/n) ")
if choice == "y" or choice == "Y":
try:
self.data.drop([column], axis=1, inplace=True)
except KeyError:
print("No column present with this name. Try again......")
continue
print("Done.......")
break
else:
print("Try again with the correct column name...")
return
def printData(self):
print(self.data)
# main function of the Preprocessor class.
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? (Press -1 to exit): "))
except ValueError:
print("Integer Value required. Try again.....")
continue
break
if choice == -1:
exit()
# moves the control into the DataDescription class.
elif choice == 1:
DataDescription(self.data).describe()
# moves the control into the Imputation class.
elif choice == 2:
self.data = Imputation(self.data).imputer()
# moves the control into the Categorical class.
elif choice == 3:
self.data = Categorical(self.data).categoricalMain()
# moves the control into the FeatureScaling class.
elif choice == 4:
self.data = FeatureScaling(self.data).scaling()
# moves the control into the Download class.
elif choice == 5:
Download(self.data).download()
else:
print("\nWrong Integer value!! Try again..")
def __init__(self):
self.data = DataInput().inputFunction()
print("\n\n" +
"WELCOME TO THE MACHINE LEARNING PREPROCESSOR CLI!!!\n" + "\n\n")
class Preprocessor:
bold_text_start = "\033[1m"
bold_text_end = "\033[0;0m"
tasks = [
'1. Data Description', '2. Handling NULL values',
'3. Encoding Categorical Data', '4. Feature Scaling of the Dataset',
'5. Download the Modified Dataset'
]
data = 0
def __init__(self):
self.data = DataInput().inputFunction()
print("\n\n" + self.bold_text_start +
"MACHINE LEARNING PREPROCESSOR CLI" + self.bold_text_end +
"\n\n")
def removeTargetColumn(self):
print("Columns\n")
for column in self.data.columns.values:
print(column, end=" ")
while (1):
column = input(
"\nWhich is the target variable:[enter -1 to exit] ").lower()
if column == "-1":
exit()
choice = input("Are you sure?(y/n) ")
if choice == "y" or choice == "Y":
try:
self.data.drop([column], axis=1, inplace=True)
except KeyError:
print("No column present with this name. Try again......")
continue
print("Done......")
break
else:
print("Try again with the correct column name...")
return
def printData(self):
print(self.data)
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 __init__(self):
self.data = DataInput().inputFunction()
print("\n\n" + self.bold_text_start +
"MACHINE LEARNING PREPROCESSOR CLI" + self.bold_text_end +
"\n\n")