classify nationalities

repl_list = ['s/o','d/o','w/o','/','&',',','-']

def clean_data(name):
	name = str(name).lower()
	name = (''.join(i for i in name if ord(i)<128)).strip()
	for repl in repl_list:
		name = name.replace(repl," ")
	if '@' in name:
		pos = name.find('@')
		name = name[:pos].strip()
	name = name.split(" ")
	name = " ".join([each.strip() for each in name])
	return name

def remove_records(merged_data):
	merged_data['delete'] = 0
	merged_data.loc[merged_data['name'].str.find('with') != -1,'delete'] = 1	
	merged_data.loc[merged_data['count_words']>=5,'delete']=1
	merged_data.loc[merged_data['count_words']==0,'delete']=1
	merged_data.loc[merged_data['name'].str.contains(r'\d') == True,'delete']=1
	cleaned_data = merged_data[merged_data.delete==0]
	return cleaned_data

merged_data = pd.concat((male_data,female_data),axis=0)

merged_data['name'] = merged_data['name'].apply(clean_data)
merged_data['count_words'] = merged_data['name'].str.split().apply(len)

cleaned_data = remove_records(merged_data)

indian_cleaned_data = cleaned_data[['name','count_words']].drop_duplicates(subset='name',keep='first')
indian_cleaned_data['label'] = 'indian'

len(indian_cleaned_data)