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

# 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()

# Converting two unique factor column into boolean
for column in ds_jobs_transformed.columns:
    unique_vals = ds_jobs_transformed[column].unique()
    if len(unique_vals) == 2:
        ds_jobs_transformed[column] = ds_jobs_transformed[column] == unique_vals[0]

# Converting integer column into int32
for column in ds_jobs_transformed.columns:
    if ds_jobs_transformed[column].dtype == 'int64':
        ds_jobs_transformed[column] = ds_jobs_transformed[column].astype('int32')

# Converting float column into float32  
for column in ds_jobs_transformed.columns:
    if ds_jobs_transformed[column].dtype == 'float64':
        ds_jobs_transformed[column] = ds_jobs_transformed[column].astype('float16')

# Manual filtering of nominal categorical column
nominal_col = ["city", "gender", "major_discipline", "company_type"]
# Converting nominal categorical column into category
for column in ds_jobs_transformed.columns:
    if column in nominal_col:
        ds_jobs_transformed[column] = ds_jobs_transformed[column].astype('category')

# Manual filtering of ordinal categorical column
ordinal_col = ["education_level",  "enrolled_university","experience", "company_size", "last_new_job"]

# Converting ordinal categorical column
for col in ordinal_col:
    print(col + " values")
    print(ds_jobs_transformed[col].unique())
    print()

# Education level order
education_order = pd.CategoricalDtype(['no_enrollment', 'High School', 'Graduate', 'Masters', 'Phd'], ordered=True)
ds_jobs_transformed["education_level"] = ds_jobs_transformed["education_level"].astype(education_order)


# Enrolled university order
education_order = pd.CategoricalDtype(['Primary School', 'Part time course', 'Full time course'], ordered=True)
ds_jobs_transformed["enrolled_university"] = ds_jobs_transformed["enrolled_university"].astype(education_order)

# Experience order
experience_order = pd.CategoricalDtype(
    ['<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["experience"] = ds_jobs_transformed["experience"].astype(experience_order)

# Company size order
company_size_order = pd.CategoricalDtype(['<10', '10-49', '50-99', '100-499', '500-999', '1000-4999', '5000-9999', '10000+'], ordered=True)
ds_jobs_transformed["company_size"] = ds_jobs_transformed["company_size"].astype(company_size_order)

# Last new job order
last_job_order = pd.CategoricalDtype(['>4', '4', '3', '2', '1', 'never'], ordered=True)
ds_jobs_transformed["last_new_job"] = ds_jobs_transformed["last_new_job"].astype(last_job_order)

# Filtering student
ds_jobs_transformed = ds_jobs_transformed[ds_jobs_transformed["experience"].cat.codes >= experience_order.categories.get_loc('10')]

# Filtering employees companies
ds_jobs_transformed = ds_jobs_transformed[ds_jobs_transformed["company_size"].cat.codes >= company_size_order.categories.get_loc('1000-4999')]


ds_jobs_transformed.head()
#ds_jobs.info()
ds_jobs_transformed.info()