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()

#information on ds_jobs
ds_jobs_info = ds_jobs_transformed.info()
print(ds_jobs_info)

#unique values in dataset
ds_jobs_unique = ds_jobs_transformed.nunique()
#unique values in education_level column
ds_jobs_transformed["education_level"].unique()
#unique values in experience column
ds_jobs_transformed["experience"].unique()
#unique values in comapny_size column
ds_jobs_transformed["company_size"].unique()
#unique values in last_new_job column
ds_jobs_transformed["last_new_job"].unique()

# EDA to help identify ordinal, nominal, and two-factor categories
for col in ds_jobs.select_dtypes("object").columns:
    print(ds_jobs_transformed[col].value_counts(), '\n')

# Create a dictionary of columns containing ordered categorical data
ordered_cats = {
    'enrolled_university': ['no_enrollment', 'Part time course', 'Full time course'],
    'education_level': ['Primary School', 'High School', 'Graduate', 'Masters', 'Phd'],
    'experience': ['<1'] + list(map(str, range(1, 21))) + ['>20'],
    'company_size': ['<10', '10-49', '50-99', '100-499', '500-999', '1000-4999', '5000-9999', '10000+'],
    'last_new_job': ['never', '1', '2', '3', '4', '>4']
}

# Create a mapping dictionary of columns containing two-factor categories to convert to Booleans
two_factor_cats = {
    'relevant_experience': {'No relevant experience': False, 'Has relevant experience': True},
    'job_change': {0.0: False, 1.0: True}
}

# Loop through DataFrame columns to efficiently change data types
for col in ds_jobs_transformed:
    
    # Convert two-factor categories to bool
    if col in ['relevant_experience', 'job_change']:
        ds_jobs_transformed[col] = ds_jobs_transformed[col].map(two_factor_cats[col])

#check data types of each columns:
ds_jobs_data_types = ds_jobs_transformed.dtypes
print(ds_jobs_data_types)

#convert experience to ordered categorical:
experience_order = ['<1', '1', '2', '3', '4', '5', '6', '7', '8', '9',
                    '10', '11', '12', '13', '14', '15', '16', '17',
                    '18', '19', '20', '>20']

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

Hidden output

#convert last_new_job to ordered categorical:
last_new_job_order = ['never', '>4', '4', '3', '2', '1']

ds_jobs_transformed["last_new_job"] = pd.Categorical(
    ds_jobs_transformed["last_new_job"],
    categories=last_new_job_order,
    ordered=True
)
ds_jobs_transformed["last_new_job"].dtype

# Convert specified columns to categorical type
categorical_columns = ['gender', 'city', 'enrolled_university', 
                       'education_level', 'major_discipline', 
                       'company_size', 'company_type']

for col in categorical_columns:
    ds_jobs_transformed[col] = ds_jobs_transformed[col].astype('category')
ds_jobs_transformed.dtypes

from pandas.api.types import CategoricalDtype

# Define ordered category for 'enrolled_university'
enrolled_order = CategoricalDtype(
    categories=['no_enrollment', 'Part time course', 'Full time course'],
    ordered=True
)
ds_jobs_transformed['enrolled_university'] = ds_jobs_transformed['enrolled_university'].astype(enrolled_order)

#education_order
education_order = CategoricalDtype(
    categories=[
        'Primary School', 
        'High School', 
        'Graduate', 
        'Masters', 
        'Phd'
    ],
    ordered=True
)

ds_jobs_transformed['education_level'] = ds_jobs_transformed['education_level'].astype(education_order)

#company_size_order:
company_size_order = CategoricalDtype(
    categories=[
        '<10', 
        '10-49', 
        '50-99', 
        '100-500', 
        '500-999', 
        '1000-4999', 
        '5000-9999', 
        '10000+'
    ],
    ordered=True
)

ds_jobs_transformed['company_size'] = ds_jobs_transformed['company_size'].astype(company_size_order)

#converting student_id into int32
ds_jobs_transformed["student_id"] = ds_jobs_transformed["student_id"].astype("int32")

#converting training_hours into int32
ds_jobs_transformed["training_hours"] = ds_jobs_transformed["training_hours"].astype("int32")

ds_jobs_transformed.dtypes

#convert city_development_index into float16:
ds_jobs_transformed["city_development_index"] = ds_jobs_transformed["city_development_index"].astype("float16")

ds_jobs_transformed.dtypes

Hidden output

# Filter students with 10 or more years experience at companies with at least 1000 employees
ds_jobs_transformed = ds_jobs_transformed[(ds_jobs_transformed['experience'] >= '10') & (ds_jobs_transformed['company_size'] >= '1000-4999')]

‌
‌
‌