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()

ds_jobs_transformed.value_counts()

ds_jobs_transformed["last_new_job"].value_counts()

ds_jobs_transformed["company_size"].value_counts()

ds_jobs_transformed.info()

ds_jobs_transformed['experience'].value_counts()

To Bool: job_change, gender, relevant_experience To int32: training_hours,student_id To float16: city_development_index To Category: education_level, enrolled_university, major_discipline, company_type To ordered categories: last_new_job, company_size

# Convert to Bool
ds_jobs_transformed["job_change"] = ds_jobs_transformed["job_change"].astype(bool)
ds_jobs_transformed["relevant_experience"] = ds_jobs_transformed["relevant_experience"].astype(bool)

# Convert to int32
int_columns = ["training_hours", "student_id"]

for col in int_columns:
    if col in ds_jobs_transformed.columns:
        ds_jobs_transformed[col] = ds_jobs_transformed[col].astype("int32", errors = "ignore")
        
# Convert to float16
ds_jobs_transformed["city_development_index"] = ds_jobs_transformed["city_development_index"].astype("float16", errors = "ignore")

# Convert categorical columns
categorical_columns = ['major_discipline', 'company_type', 'gender', 'city']
for col in categorical_columns:
    if col in ds_jobs_transformed.columns:
        ds_jobs_transformed[col] = ds_jobs_transformed[col].astype("category")
     
# Convert ordered(ordinal) categorical columns
# Handle experience as an ordered category
if 'experience' in ds_jobs_transformed.columns:
    experience_order = [
            '<1',
            '1',
            '2',
            '3',
            '4',
            '5',
            '6',
            '7',
            '8',
            '9',
            '10',
            '11',
            '12',
            '13',
            '14',
            '15',
            '16',
            '17',
            '18',
            '19',
            '20',
            '>20'
        ]
experience_dtype = pd.CategoricalDtype(categories=experience_order, ordered=True)
ds_jobs_transformed['experience'] = ds_jobs_transformed['experience'].astype(experience_dtype) 

# Handle education_level as an ordered category
if "education_level" in ds_jobs_transformed.columns:
    education_order = ['Primary School', 'High School', 'Graduate', 'Masters', 'Phd']
    education_dtype = pd.CategoricalDtype(categories = education_order, ordered= True)
    ds_jobs_transformed["education_level"] = ds_jobs_transformed["education_level"].astype(education_dtype)


# Handle enrolled_university as an ordered category
if "enrolled_university" in ds_jobs_transformed.columns:
    enrollment_order = ['no_enrollment', 'Part time course', 'Full time course']
    enrollment_dtype = pd.CategoricalDtype(categories = enrollment_order, ordered= True)
    ds_jobs_transformed["enrolled_university"] = ds_jobs_transformed["enrolled_university"].astype(enrollment_dtype)

# Define order for last_new_job
if "last_new_job" in ds_jobs_transformed.columns:
    job_order = ['never', '1', '2', '3', '4', '>4']
    ds_jobs_transformed["last_new_job"] = pd.Categorical(
        ds_jobs_transformed["last_new_job"],
        categories = job_order,
        ordered=True
    )

# Define order for company_size
if "company_size" in ds_jobs_transformed.columns:
    size_order = ['<10', '10-49', '50-99', '100-499', '500-999', '1000-4999', '5000-9999', '10000+']
    ds_jobs_transformed["company_size"] = pd.Categorical(
        ds_jobs_transformed["company_size"],
        categories = size_order,
        ordered=True
    )

# Create mask for large companies (≥1000 employees)
large_company_mask = ds_jobs_transformed['company_size'].isin(['1000-4999', '5000-9999', '10000+'])

experienced_mask = ds_jobs_transformed['experience'].isin([
    '10', '11', '12', '13', '14', '15', '16', '17', '18', '19', '20', '>20'
])

ds_jobs_transformed = ds_jobs_transformed[large_company_mask & experienced_mask]

print(ds_jobs.info())
print(ds_jobs_transformed.info())