# Install required packages
!pip install --quiet pandas
import os
import urllib.request
import zipfile
# Download and extract data files
url = 'https://github.com/jsoma/workshop-newsroom-ai-infra/raw/main/docs/04-transfer-data/04-transfers-data.zip'
print(f'Downloading data from {url}...')
urllib.request.urlretrieve(url, '04-transfers-data.zip')
print('Extracting 04-transfers-data.zip...')
with zipfile.ZipFile('04-transfers-data.zip', 'r') as zip_ref:
zip_ref.extractall('.')
os.remove('04-transfers-data.zip')
print('✓ Data files extracted!')
We aren't doing anything fancy here! But it's just some data analysis we don't want to have to do for other people.
import pandas as pd
pd.options.display.max_columns = None
df = pd.read_csv("data/transfers.csv")
df.head()
df[df['source_year'] == 2017].head()
df['assessment_total'].median()