few details and README Added

Author: MuizZer07

README.md

@@ -1,5 +1,5 @@
 # Data-Generator
-This code is to generate random dataset of Bangladeshi people's profile. A few attributes were considered like a person's NID, 
+This code is to generate random dataset of **Bangladeshi people's profile**. A few attributes were considered like a person's NID, 
 name (first-name, middle name, last name), father's name (first-name, middle name, last name), mother's name (first-name, middle name, 
 last name), present address (house number, street, ward number, area, thana (Police Station), city, district, division) for people 
 living in cities, present address ( ward number, village, thana (Police Station), district, division) for people living in villages, 
@@ -9,6 +9,7 @@ mobile, email if any, marital status, gender, place of birth, Passport number if
 person (name as above, address as above, mobile and email), income, asset, tax, educational qualification (SSC, HSC, graduation,
 post graduation, PhD).
 
+## Procedure
 First, a list of Bangladeshi people's names (in names1.csv file) were collected from the internet. All the names were fragmented to 
 single names. Then different tags were assigned to each of them based on whether the name is a male or female name (gender), whether it 
 is a Muslim, or other religion's name and whether it is a first, middle or last name (Positioning). Tags were used to generate more 
@@ -23,3 +24,18 @@ of the fields were given and then randomly picked from them. For educational qua
 passed S.S.C from), H.S.C result, college (where a person passed H.S.C from), under graduation result, university, post graduation 
 result, university were generated. Other personal information like marital status, height, weight also generated randomly.
 
+### Package installation
+The scripts requires some libraries to be installed before executing. By running the following code all the required modules can be installed.
+```sh
+$ pip install -r requirements.txt
+```
+
+### Run
+```sh
+$ python main.py
+```
+
+It will take one input asking for how many rows to generate in the first line.
+
+**Thank You**
+

data_generator.py

@@ -1,10 +1,19 @@
 import random
 import string
-
+import math
 
 class Data_Generator():
 
-    def __init__(self):
+    """
+    Generates profile according to given names.
+    Different attributes generated randomly.
+    """
+    
+    def __init__(self, limit):
+        
+        self.limit = limit
+        self.mul = math.ceil(limit/350000)
+            
         self.marital_status = {
             1: 'Single',
             2: 'Married',
@@ -304,78 +313,78 @@ def __init__(self):
             self.new_generated_ec_mobile.append(self.generate_phone_no())
             self.new_generated_ec_email.append(self.generate_email(ec_fname, ec_lname))
 
-    def get_data(self, limit):
-        Data = {'First name': self.new_generated_first_names[:limit],
-                'Middle name': self.new_generated_middle_names[:limit],
-                'Last name': self.new_generated_last_names[:limit],
-                'NID': self.new_generated_NID[:limit],
-                'Fathers First Name': self.new_generated_fathers_first_name[:limit],
-                'Fathers Middle Name': self.new_generated_fathers_middle_name[:limit],
-                'Fathers Last Name': self.new_generated_fathers_last_name[:limit],
-                'Mothers First Name': self.new_generated_mothers_first_name[:limit],
-                'Mothers Middle Name': self.new_generated_mothers_middle_name[:limit],
-                'Mothers Last Name': self.new_generated_mothers_last_name[:limit],
-                'Sex': self.new_generated_sex[:limit],
-                'Religion': self.new_generated_religion[:limit],
-                'Marital Status': self.new_generated_marital_status[:limit],
-                'Height': self.new_generated_height[:limit],
-                'Weight': self.new_generated_weight[:limit],
-                'Profession': self.new_generated_profession[:limit],
-                'Income': self.new_generated_salary[:limit],
-                'Income Tax' : self.new_generated_income_tax[:limit],
-                'TIN No': self.new_generated_tin_no[:limit],
-                'Assets': self.new_generated_assets[:limit],
-                'Date of Birth': self.new_generated_DOB[:limit],
-                'Passport No': self.new_generated_passport_no[:limit],
-                'Email Address': self.new_generated_emails[:limit],
-                'Mobile No': self.new_generated_mobile_no[:limit],
-                'Prsnt_addr_house_no': self.new_generated_present_addr_house_no[:limit],
-                'Prsnt_addr_street_no': self.new_generated_present_addr_street_no[:limit],
-                'Prsnt_addr_ward_no': self.new_generated_present_addr_word_no[:limit],
-                'Prsnt_addr_village': self.new_generated_present_addr_village[:limit],
-                'Prsnt_addr_thana': self.new_generated_present_addr_thana[:limit],
-                'Prsnt_addr_city': self.new_generated_present_addr_city[:limit],
-                'Prsnt_addr_district': self.new_generated_present_addr_district[:limit],
-                'Prsnt_addr_division': self.new_generated_present_addr_division[:limit],                
-                'Prmntn_addr_house_no': self.new_generated_permanent_addr_house_no[:limit],
-                'Prmntn_addr_street_no': self.new_generated_permanent_addr_street_no[:limit],
-                'Prmntn_addr_ward_no': self.new_generated_permanent_addr_word_no[:limit],
-                'Prmntn_addr_village': self.new_generated_permanent_addr_village[:limit],
-                'Prmntn_addr_thana': self.new_generated_permanent_addr_thana[:limit],
-                'Prmntn_addr_city': self.new_generated_permanent_addr_city[:limit],
-                'Prmntn_addr_district': self.new_generated_permanent_addr_district[:limit],
-                'Prmntn_addr_division': self.new_generated_permanent_addr_division[:limit],
-                'SSC Passed From': self.new_generated_school[:limit],
-                'SSC Result': self.new_generated_SSC_gpa[:limit],
-                'HSC Passed From': self.new_generated_college[:limit],
-                'HSC Result': self.new_generated_HSC_gpa[:limit],
-                'Graduated From': self.new_generated_ug[:limit],
-                'Undergrad Result': self.new_generated_ug_cgpa[:limit],
-                'Post Graduated From': self.new_generated_grad[:limit],
-                'Postgrad Result': self.new_generated_grad_cgpa[:limit],
-                'Doctorate From': self.new_generated_phd[:limit],
-                'Place of Birth': self.new_generated_place_of_birth[:limit],
-                'EC First Name': self.new_generated_ec_firstname[:limit],
-                'EC Middle Name': self.new_generated_ec_middlename[:limit],
-                'EC Last Name': self.new_generated_ec_lastname[:limit],
-                'EC_Prsnt_addr_house_no': self.new_generated_ec_present_addr_house_no[:limit],
-                'EC_Prsnt_addr_street_no': self.new_generated_ec_present_addr_street_no[:limit],
-                'EC_Prsnt_addr_ward_no': self.new_generated_ec_present_addr_word_no[:limit],
-                'EC_Prsnt_addr_village': self.new_generated_ec_present_addr_village[:limit],
-                'EC_Prsnt_addr_thana': self.new_generated_ec_present_addr_thana[:limit],
-                'EC_Prsnt_addr_city': self.new_generated_ec_present_addr_city[:limit],
-                'EC_Prsnt_addr_district': self.new_generated_ec_present_addr_district[:limit],
-                'EC_Prsnt_addr_division': self.new_generated_ec_present_addr_division[:limit],                
-                'EC_Prmntn_addr_house_no': self.new_generated_ec_permanent_addr_house_no[:limit],
-                'EC_Prmntn_addr_street_no': self.new_generated_ec_permanent_addr_street_no[:limit],
-                'EC_Prmntn_addr_ward_no': self.new_generated_ec_permanent_addr_word_no[:limit],
-                'EC_Prmntn_addr_village': self.new_generated_ec_permanent_addr_village[:limit],
-                'EC_Prmntn_addr_thana': self.new_generated_ec_permanent_addr_thana[:limit],
-                'EC_Prmntn_addr_city': self.new_generated_ec_permanent_addr_city[:limit],
-                'EC_Prmntn_addr_district': self.new_generated_ec_permanent_addr_district[:limit],
-                'EC_Prmntn_addr_division': self.new_generated_ec_permanent_addr_division[:limit],
-                'EC Mobile No': self.new_generated_ec_mobile[:limit],
-                'EC Email Address': self.new_generated_ec_email[:limit],
+    def get_data(self):
+        Data = {'First name': self.new_generated_first_names[:self.limit],
+                'Middle name': self.new_generated_middle_names[:self.limit],
+                'Last name': self.new_generated_last_names[:self.limit],
+                'NID': self.new_generated_NID[:self.limit],
+                'Fathers First Name': self.new_generated_fathers_first_name[:self.limit],
+                'Fathers Middle Name': self.new_generated_fathers_middle_name[:self.limit],
+                'Fathers Last Name': self.new_generated_fathers_last_name[:self.limit],
+                'Mothers First Name': self.new_generated_mothers_first_name[:self.limit],
+                'Mothers Middle Name': self.new_generated_mothers_middle_name[:self.limit],
+                'Mothers Last Name': self.new_generated_mothers_last_name[:self.limit],
+                'Sex': self.new_generated_sex[:self.limit],
+                'Religion': self.new_generated_religion[:self.limit],
+                'Marital Status': self.new_generated_marital_status[:self.limit],
+                'Height': self.new_generated_height[:self.limit],
+                'Weight': self.new_generated_weight[:self.limit],
+                'Profession': self.new_generated_profession[:self.limit],
+                'Income': self.new_generated_salary[:self.limit],
+                'Income Tax' : self.new_generated_income_tax[:self.limit],
+                'TIN No': self.new_generated_tin_no[:self.limit],
+                'Assets': self.new_generated_assets[:self.limit],
+                'Date of Birth': self.new_generated_DOB[:self.limit],
+                'Passport No': self.new_generated_passport_no[:self.limit],
+                'Email Address': self.new_generated_emails[:self.limit],
+                'Mobile No': self.new_generated_mobile_no[:self.limit],
+                'Prsnt_addr_house_no': self.new_generated_present_addr_house_no[:self.limit],
+                'Prsnt_addr_street_no': self.new_generated_present_addr_street_no[:self.limit],
+                'Prsnt_addr_ward_no': self.new_generated_present_addr_word_no[:self.limit],
+                'Prsnt_addr_village': self.new_generated_present_addr_village[:self.limit],
+                'Prsnt_addr_thana': self.new_generated_present_addr_thana[:self.limit],
+                'Prsnt_addr_city': self.new_generated_present_addr_city[:self.limit],
+                'Prsnt_addr_district': self.new_generated_present_addr_district[:self.limit],
+                'Prsnt_addr_division': self.new_generated_present_addr_division[:self.limit],                
+                'Prmntn_addr_house_no': self.new_generated_permanent_addr_house_no[:self.limit],
+                'Prmntn_addr_street_no': self.new_generated_permanent_addr_street_no[:self.limit],
+                'Prmntn_addr_ward_no': self.new_generated_permanent_addr_word_no[:self.limit],
+                'Prmntn_addr_village': self.new_generated_permanent_addr_village[:self.limit],
+                'Prmntn_addr_thana': self.new_generated_permanent_addr_thana[:self.limit],
+                'Prmntn_addr_city': self.new_generated_permanent_addr_city[:self.limit],
+                'Prmntn_addr_district': self.new_generated_permanent_addr_district[:self.limit],
+                'Prmntn_addr_division': self.new_generated_permanent_addr_division[:self.limit],
+                'SSC Passed From': self.new_generated_school[:self.limit],
+                'SSC Result': self.new_generated_SSC_gpa[:self.limit],
+                'HSC Passed From': self.new_generated_college[:self.limit],
+                'HSC Result': self.new_generated_HSC_gpa[:self.limit],
+                'Graduated From': self.new_generated_ug[:self.limit],
+                'Undergrad Result': self.new_generated_ug_cgpa[:self.limit],
+                'Post Graduated From': self.new_generated_grad[:self.limit],
+                'Postgrad Result': self.new_generated_grad_cgpa[:self.limit],
+                'Doctorate From': self.new_generated_phd[:self.limit],
+                'Place of Birth': self.new_generated_place_of_birth[:self.limit],
+                'EC First Name': self.new_generated_ec_firstname[:self.limit],
+                'EC Middle Name': self.new_generated_ec_middlename[:self.limit],
+                'EC Last Name': self.new_generated_ec_lastname[:self.limit],
+                'EC_Prsnt_addr_house_no': self.new_generated_ec_present_addr_house_no[:self.limit],
+                'EC_Prsnt_addr_street_no': self.new_generated_ec_present_addr_street_no[:self.limit],
+                'EC_Prsnt_addr_ward_no': self.new_generated_ec_present_addr_word_no[:self.limit],
+                'EC_Prsnt_addr_village': self.new_generated_ec_present_addr_village[:self.limit],
+                'EC_Prsnt_addr_thana': self.new_generated_ec_present_addr_thana[:self.limit],
+                'EC_Prsnt_addr_city': self.new_generated_ec_present_addr_city[:self.limit],
+                'EC_Prsnt_addr_district': self.new_generated_ec_present_addr_district[:self.limit],
+                'EC_Prsnt_addr_division': self.new_generated_ec_present_addr_division[:self.limit],                
+                'EC_Prmntn_addr_house_no': self.new_generated_ec_permanent_addr_house_no[:self.limit],
+                'EC_Prmntn_addr_street_no': self.new_generated_ec_permanent_addr_street_no[:self.limit],
+                'EC_Prmntn_addr_ward_no': self.new_generated_ec_permanent_addr_word_no[:self.limit],
+                'EC_Prmntn_addr_village': self.new_generated_ec_permanent_addr_village[:self.limit],
+                'EC_Prmntn_addr_thana': self.new_generated_ec_permanent_addr_thana[:self.limit],
+                'EC_Prmntn_addr_city': self.new_generated_ec_permanent_addr_city[:self.limit],
+                'EC_Prmntn_addr_district': self.new_generated_ec_permanent_addr_district[:self.limit],
+                'EC_Prmntn_addr_division': self.new_generated_ec_permanent_addr_division[:self.limit],
+                'EC Mobile No': self.new_generated_ec_mobile[:self.limit],
+                'EC Email Address': self.new_generated_ec_email[:self.limit],
                 }
 
         columns = ['First name', 'Middle name', 'Last name', 'NID', 'Fathers First Name', \
@@ -406,11 +415,11 @@ def generate_profile(self, first_names, middle_names, last_names, gender, religi
             for lastname in last_names:
                 if middle_names != None:
                     for middlename in middle_names:
-                        for i in range(2):
+                        for i in range(self.mul):
                             self.generate_single_profile(first_names, last_names, firstname, middlename, lastname, gender, religion)
 #                        
                 else:
-                    for i in range(2):
+                    for i in range(self.mul):
                         self.generate_single_profile(first_names, last_names, firstname, None, lastname, gender, religion)
 
     def generate_single_profile(self, first_names, last_names, firstname, middlename, lastname, gender, religion):

data_loader.py

@@ -3,6 +3,10 @@
 
 class Data_Loader():
 
+    """
+    Loads csv file into a Pandas DataFrame by shuffling all rows.
+    Fragments names by poistioning, religion and gender.
+    """
 
     def __init__(self, Data=None):
         self.dataframe = Data

main.py

@@ -2,18 +2,26 @@
 from data_generator import Data_Generator
 
 if __name__ == "__main__":
+    
+    # Enter how many rows to generate
+    limit = int(input("Enter number of rows to generate: "))
+    
+    # Initializing classes, Data_Loader(), Data_Generator
     loader = Data_Loader()
-    generator = Data_Generator()
+    generator = Data_Generator(limit)
 
+    # Loads signle names from a csv file into a dataframe
     filename = 'names1.csv'
     df = loader.read_csvfile(filename)
 
+    # Generates firstnames, middlenames, lastnames for every religion and gender
     for religion in loader.religion:
         for gender in loader.gender:
             firstnames, middlenames, lastnames = loader.get_names_by_religion_gender(religion, gender)
 
             for i in range(2):
                 if i % 2 == 0:
+                    # Generates 2 word length names
                     if gender == 'unisex':
                         gender1 = 'male'
                         firstnames1, middlenames1 , lastnames1 = loader.get_names_by_religion_gender(religion, gender1)
@@ -27,6 +35,7 @@
                         last_names2 = lastnames + lastnames2
                         generator.generate_profile(first_names2, None, last_names2, gender2, religion)
                 else:
+                    # Generates 3 word length names
                     if gender == 'unisex':
                         gender3 = 'male'
                         firstnames3, middlenames3 , lastnames3 = loader.get_names_by_religion_gender(religion, gender3)
@@ -41,8 +50,11 @@
                         middle_names4 = middlenames + middlenames4
                         last_names4 = lastnames + lastnames4
                         generator.generate_profile(first_names4, middle_names4, last_names4, gender4, religion)
-                        
+           
+    # Gets all data already generated by data_generator class             
     data, collumns = generator.get_data()
-    filename = 'new.csv'
+    
+    # Saves all rows and columns into a csv file
+    filename = str(limit) + '_rows.csv'
     saved_data = loader.save_csvfile(filename, data, collumns)
     print(saved_data)

requirements.txt

@@ -0,0 +1,2 @@
+pandas==0.23.4
+scikit-learn==0.20.1