Project: Customer Analytics: Preparing Data for Modeling

A common problem when creating models to generate business value from data is that the datasets can be so large that it can take days for the model to generate predictions. Ensuring that your dataset is stored as efficiently as possible is crucial for allowing these models to run on a more reasonable timescale without having to reduce the size of the dataset.

You've been hired by a major online data science training provider called Training Data Ltd. to clean up one of their largest customer datasets. This dataset will eventually be used to predict whether their students are looking for a new job or not, information that they will then use to direct them to prospective recruiters.

You've been given access to customer_train.csv, which is a subset of their entire customer dataset, so you can create a proof-of-concept of a much more efficient storage solution. The dataset contains anonymized student information, and whether they were looking for a new job or not during training:

Column	Description
`student_id`	A unique ID for each student.
`city`	A code for the city the student lives in.
`city_development_index`	A scaled development index for the city.
`gender`	The student's gender.
`relevant_experience`	An indicator of the student's work relevant experience.
`enrolled_university`	The type of university course enrolled in (if any).
`education_level`	The student's education level.
`major_discipline`	The educational discipline of the student.
`experience`	The student's total work experience (in years).
`company_size`	The number of employees at the student's current employer.
`company_type`	The type of company employing the student.
`last_new_job`	The number of years between the student's current and previous jobs.
`training_hours`	The number of hours of training completed.
`job_change`	An indicator of whether the student is looking for a new job (`1`) or not (`0`).

# Import necessary libraries
import pandas as pd
import numpy as np

# Load the dataset
ds_jobs = pd.read_csv("customer_train.csv")

# View the dataset
ds_jobs.head()

# Create a copy of ds_jobs for transforming
ds_jobs_transformed = ds_jobs.copy()

# Start coding here. Use as many cells as you like!

#Transformar as colunas que serao utilizadas no subseting em categorias

ds_jobs_transformed['experience'] = ds_jobs_transformed['experience'].astype('category')
ds_jobs_transformed['company_size'] = ds_jobs_transformed['company_size'].astype('category')
#ds_jobs_transformed['experience'].value_counts()



#Ordenar as categorias experience e company_size para realizar os filtros de trabalhadores com mais de 10 anos de experiencia em grandes empresas
#O sorting dessas categorias só fica claro quando usamos o .sort_index() nas visualizacoes

ds_jobs_transformed['experience'] = ds_jobs_transformed['experience'].cat.reorder_categories(new_categories = ['<1','1','2','3','4','5','6','7','8','9','10','11','12','13','14','15','16','17','18','19','20','>20'] , ordered = True)

ds_jobs_transformed['company_size'] = ds_jobs_transformed['company_size'].cat.reorder_categories(new_categories = ['<10','10-49','50-99','100-499','500-999','1000-4999','5000-9999','10000+'], ordered = True)

#Filtrar o dataset

ds_jobs_transformed = ds_jobs_transformed.loc[(ds_jobs_transformed['experience'] >= '10') & (ds_jobs_transformed['company_size'] >= '1000-4999') , :]

#Alterar colunas "relevant_experience" e "job change" para bool
#alteração da coluna relevant_experience para 0,1
ds_jobs_transformed['relevant_experience'] = np.where(ds_jobs_transformed['relevant_experience'] == 'Has relevant experience', 1,0)
#alteracao do tipo de ambas as colunas para bool
ds_jobs_transformed['relevant_experience'] = ds_jobs_transformed['relevant_experience'].astype('bool')
ds_jobs_transformed['job_change'] = ds_jobs_transformed['job_change'].astype('bool')

#Alterar colunas "student_id" e "training_hours" para int32
ds_jobs_transformed['student_id'] = ds_jobs_transformed['student_id'].astype('int32')
ds_jobs_transformed['training_hours'] = ds_jobs_transformed['training_hours'].astype('int32')

#Alterar coluna "city_development_index" para float16
ds_jobs_transformed['city_development_index'] = ds_jobs_transformed['city_development_index'].astype('float16')

#Alterar colunas 'city' 'gender', 'major_discipline', 'company_type' para category data type
ds_jobs_transformed['city'] = ds_jobs_transformed['city'].astype('category')
ds_jobs_transformed['gender'] = ds_jobs_transformed['gender'].astype('category')
ds_jobs_transformed['major_discipline'] = ds_jobs_transformed['major_discipline'].astype('category')
ds_jobs_transformed['company_type'] = ds_jobs_transformed['company_type'].astype('category')


#Alterar colunas 'enrolled_university', 'education_level', 'last_new_job' para ordered category data type
ds_jobs_transformed['enrolled_university'] = ds_jobs_transformed['enrolled_university'].astype('category')
ds_jobs_transformed['education_level'] = ds_jobs_transformed['education_level'].astype('category')
ds_jobs_transformed['last_new_job'] = ds_jobs_transformed['last_new_job'].astype('category')


ds_jobs_transformed['enrolled_university'] = ds_jobs_transformed['enrolled_university'].cat.reorder_categories(new_categories = ['no_enrollment','Part time course', 'Full time course'], ordered = True)
ds_jobs_transformed['education_level'] = ds_jobs_transformed['education_level'].cat.reorder_categories(new_categories = ['Primary School','High School','Graduate','Masters','Phd'], ordered = True)
ds_jobs_transformed['last_new_job'] = ds_jobs_transformed['last_new_job'].cat.reorder_categories(new_categories = ['never','1','2','3','4','>4'], ordered = True)

#CAMPO DE TESTES

#print(ds_jobs_transformed['experience'].value_counts(dropna = False))
#print(ds_jobs_transformed['company_size'].value_counts().sort_index())

#ds_jobs_transformed['last_new_job'].value_counts().sort_index()

#ds_jobs_transformed['job_change'].value_counts()

print(ds_jobs.info())

print(ds_jobs_transformed.info())