deanjamesss

select e.userid as employee_no,
       e.dob    as date_of_birth
from employee e
where e.first_name = 'Dean'
  and e.surname = 'McGrath'

deanjamesss

select p.item_name      as product_title,
       p.cost           as cost_price,
       p.units          as unit_count,
       p.cost * p.units as inventory_cost
from product p
where p.type in ('storage', 'cables')
  and p.item_name like '%USB%'

deanjamesss

deanjamesss

import pandas as pd


def load_csv_file():
    df = pd.read_csv('getting_started_test_data.csv')
    
    print(df.info())
    print(df.describe(include='all'))
    print(df.head(5))

deanjamesss

import numpy as np
import pandas as pd
import pandas_profiling
from faker import Faker


def build_fake_data(size=1):
    fake = Faker()
    output = [{'name': fake.name(),
               'address': fake.address(),

deanjamesss

deanjamesss

import pandas as pd

if __name__ == '__main__':
    # Override default pandas configuration
    pd.options.display.width = 0
    pd.options.display.max_rows = 10000
    pd.options.display.max_info_columns = 10000

    # Open example data.
    df = pd.read_csv('employee_data.csv')

deanjamesss

rows, columns = df.shape
cell_count = rows * columns
number_of_nulls = df.isnull().sum().sum()
percentage_of_missing = (number_of_nulls / cell_count) * 100
print(f'Percentage of missing values: {percentage_of_missing}%')

deanjamesss

# Check to see if any rows have less than 2 elements.
under_threshold_removed = df.dropna(axis='index', thresh=2, inplace=False)
under_threshold_rows = df[~df.index.isin(under_threshold_removed.index)]
print(under_threshold_rows)

deanjamesss

# Set a default category for missing genders.
df['gender'].cat.add_categories(new_categories=['U'], inplace=True)
df.fillna(value={'gender': 'U'}, inplace=True)
print(df.info())