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()

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

# Storing the initial memory used by the dataframe
Initial_memory = pd.DataFrame(ds_jobs_transformed.memory_usage(deep = True))
Initial_memory

# Columns containing categories with only two factors must be stored as Booleans (bool).

# Identify the columns containing categories with only two factors
ds_jobs_transformed.info()
columns_with_two_values = [col for col in ds_jobs_transformed.columns if ds_jobs_transformed[col].nunique() == 2]

# Converting the columns to boolean data type
for col in columns_with_two_values:
    ds_jobs_transformed[col] = ds_jobs_transformed[col].astype("bool")

# Verifying the changes
ds_jobs_transformed.info()

# Columns containing integers only must be stored as 32-bit integers (int32

# Identifying the columns containng integers only
columns_with_integers_only = [col for col in ds_jobs_transformed.columns if ds_jobs_transformed[col].dtype == int]

# Changing the data type of the columns with integer data only to "int32"
for col in columns_with_integers_only:
    ds_jobs_transformed[col] = ds_jobs_transformed[col].astype("int32")
    
# Verifying the changes    
ds_jobs_transformed.info()

# Columns containing floats must be stored as 16-bit floats (float16).

# Identifying the columns containng float only
columns_with_float_only = [col for col in ds_jobs_transformed.columns if ds_jobs_transformed[col].dtype == float]

# Changing the data type of the columns with float data only to "float16"
for col in columns_with_float_only:
    ds_jobs_transformed[col] = ds_jobs_transformed[col].astype("float16")
    
# Verifying the changes    
ds_jobs_transformed.info()

# Columns containing nominal categorical data must be stored as the 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")

# Looking at the Data
ds_jobs_transformed['experience'].value_counts()

# Columns containing ordinal categorical data must be stored as ordered categories, and not mapped to numerical values, with an order that reflects the natural order of the column.

# Dealing with NaN values by filling them with "Unknown" String
ds_jobs_transformed['experience'] = ds_jobs_transformed['experience'].fillna("Unknown")

# Defining ordered categories for experience
ordered_experience = ["1", "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15", "16", "17", "18", "19", "20", ">20"]
#Converting 'experience' to ordered catrgory data type
experience_dtype = pd.CategoricalDtype(categories = ordered_experience, ordered = True)
ds_jobs_transformed['experience'] = ds_jobs_transformed['experience'].astype(experience_dtype)

# Handling NaN values and setting them to "Unknown"
ds_jobs_transformed['company_size'] = ds_jobs_transformed['company_size'].fillna("Unknown")

# Define ordered categories for 'company_size'
ordered_company_size = ["<10", "10-49", "50-99", "100-499", "500-999", "1000-4999", "5000-9999", "10000+", "Unknown"]

# Convert 'company_size' to ordered categorical datatype
company_size_dtype = pd.CategoricalDtype(categories=ordered_company_size, ordered=True)
ds_jobs_transformed['company_size'] = ds_jobs_transformed['company_size'].astype(company_size_dtype)

# Handling NaN values and setting them to "Unknown"
ds_jobs_transformed['last_new_job'] = ds_jobs_transformed['last_new_job'].fillna("Unknown")

# Define ordered categories for 'last_new_job'
ordered_last_new_job = ["never", "1", "2", "3", "4", ">4", "Unknown"]

# Convert 'last_new_job' to ordered categorical datatype
last_new_job_dtype = pd.CategoricalDtype(categories=ordered_last_new_job, ordered=True)
ds_jobs_transformed['last_new_job'] = ds_jobs_transformed['last_new_job'].astype(last_new_job_dtype)

# Handling NaN values and setting them to "Unknown"
ds_jobs_transformed['enrolled_university'] = ds_jobs_transformed['enrolled_university'].fillna("Unknown")

# Define ordered categories for 'enrolled_university'
ordered_enrolled_university = ["no_enrollment", "Full time course", "Part time course", "Unknown"]

# Convert 'enrolled_university' to ordered categorical datatype
enrolled_university_dtype = pd.CategoricalDtype(categories=ordered_enrolled_university, ordered=True)
ds_jobs_transformed['enrolled_university'] = ds_jobs_transformed['enrolled_university'].astype(enrolled_university_dtype)

# Handling NaN values and setting them to "Unknown"
ds_jobs_transformed['education_level'] = ds_jobs_transformed['education_level'].fillna("Unknown")

# Define ordered categories for 'education_level'
ordered_education_level = ["Primary School", "High School", "Graduate", "Masters", "Phd", "Unknown"]

# Convert 'education_level' to ordered categorical datatype
education_level_dtype = pd.CategoricalDtype(categories=ordered_education_level, ordered=True)
ds_jobs_transformed['education_level'] = ds_jobs_transformed['education_level'].astype(education_level_dtype)

# Verifying the datatypes and checking the first few rows to ensure the conversion was successful
print(ds_jobs_transformed.info())

# The DataFrame should be filtered to only contain students with 10 or more years of experience at companies with at least 1000 employees, as their recruiter base is suited to more experienced professionals at enterprise companies.

ds_jobs_transformed = ds_jobs_transformed[(ds_jobs_transformed["experience"].isin(["10", "11", "12", "13", "14", "15", "16", "17", "18", "19", "20", ">20"])) & (ds_jobs_transformed["company_size"].isin(["1000-4999", "5000-9999", "10000+"]))]

print(f"The memory usage before transformation was: \n{ds_jobs.memory_usage()}")
print(f"\nThe memory usage after transformation was: \n{ds_jobs_transformed.memory_usage()}")