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()

# Información general
print(ds_jobs.info())

# Uso detallado de memoria
print(ds_jobs.memory_usage(deep=True))

# Valores únicos por columna
print(ds_jobs.nunique())

# Estadísticas generales, incluyendo categóricas
print(ds_jobs.describe(include='all'))

# Mapeo de experiencia laboral
experience_map = {
    '<1': 0,
    '1': 1, '2': 2, '3': 3, '4': 4, '5': 5,
    '6': 6, '7': 7, '8': 8, '9': 9,
    '10': 10, '11': 11, '12': 12, '13': 13,
    '14': 14, '15': 15, '16': 16, '17': 17,
    '18': 18, '19': 19, '20': 20, '>20': 21
}
ds_jobs_transformed['experience'] = ds_jobs_transformed['experience'].map(experience_map)

# Mapeo de tamaño de empresa (categoría ordinal)
company_size_order = ['<10', '10-49', '50-99', '100-500', '500-999',
                      '1000-4999', '5000-9999', '10000+']
ds_jobs_transformed['company_size'] = pd.Categorical(
    ds_jobs_transformed['company_size'],
    categories=company_size_order,
    ordered=True
)

# Mapeo de tiempo desde el último empleo
last_new_job_map = {
    'never': 0, '<1': 0, '1': 1, '2': 2, '3': 3, '4': 4, '>4': 5
}
ds_jobs_transformed['last_new_job'] = ds_jobs_transformed['last_new_job'].map(last_new_job_map)

# Filtrar experiencia ≥10 y empresa con tamaño ordenado ≥ '1000-4999'
filtered_df = ds_jobs_transformed[
    (ds_jobs_transformed['experience'] >= 10) &
    (ds_jobs_transformed['company_size'] >= '1000-4999')
]

# Valores únicos de experiencia
print("Valores únicos en 'experience':")
print(ds_jobs_transformed['experience'].unique())

# Valores únicos de tamaño de empresa
print("\nValores únicos en 'company_size':")
print(ds_jobs_transformed['company_size'].unique())

# Valores únicos en 'last_new_job'
print("\nValores únicos en 'last_new_job':")
print(ds_jobs_transformed['last_new_job'].unique())

# Aplicar filtro: experiencia >= 10 y tamaño de empresa >= '1000-4999'
ds_jobs_transformed = ds_jobs_transformed[
    (ds_jobs_transformed['experience'] >= 10) &
    (ds_jobs_transformed['company_size'] >= '1000-4999')
]

print(f"Número de filas tras el filtrado: {ds_jobs_transformed.shape[0]}")

# Convertir columnas binarias a bool
ds_jobs_transformed['relevant_experience'] = ds_jobs_transformed['relevant_experience'].map({
    'Has relevent experience': True,
    'No relevent experience': False
}).astype('bool')

ds_jobs_transformed['job_change'] = ds_jobs_transformed['job_change'].astype('bool')

# Convertir enteros a 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')
ds_jobs_transformed['experience'] = ds_jobs_transformed['experience'].astype('int32')
ds_jobs_transformed['last_new_job'] = ds_jobs_transformed['last_new_job'].astype('float16')  # puede ser float

# Convertir float a float16
ds_jobs_transformed['city_development_index'] = ds_jobs_transformed['city_development_index'].astype('float16')

# Convertir columnas nominales a category
nominal_cols = ['city', 'gender', 'enrolled_university', 'major_discipline', 'company_type']
for col in nominal_cols:
    ds_jobs_transformed[col] = ds_jobs_transformed[col].astype('category')


experience_order = list(range(0, 21)) + [21]  # 0 a 20, más 21 como '>20'
experience_order = [int(x) for x in experience_order]

ds_jobs_transformed['experience'] = pd.Categorical(
    ds_jobs_transformed['experience'],
    categories=experience_order,
    ordered=True
)

# Convertir 'last_new_job' a categoría ordenada
last_new_job_order = [0, 1, 2, 3, 4, 5]  # 0 = never/<1, 5 = >4
ds_jobs_transformed['last_new_job'] = pd.Categorical(
    ds_jobs_transformed['last_new_job'],
    categories=last_new_job_order,
    ordered=True
)

# Convertir columnas ordinales a categorías ordenadas
# education_level
education_order = ['Primary School', 'High School', 'Graduate', 'Masters', 'Phd']
ds_jobs_transformed['education_level'] = pd.Categorical(
    ds_jobs_transformed['education_level'],
    categories=education_order,
    ordered=True
)

# Convertir 'enrolled_university' a categoría ordenada
enrolled_order = ['no_enrollment', 'Part time course', 'Full time course']
ds_jobs_transformed['enrolled_university'] = pd.Categorical(
    ds_jobs_transformed['enrolled_university'],
    categories=enrolled_order,
    ordered=True
)

# company_size ya está en categoría ordenada desde antes
# Nueva info y memoria
print(ds_jobs_transformed.info())
print(ds_jobs_transformed.memory_usage(deep=True))