Jump to section

Food Standards Agency - Alerts Meta Data

Source data from Web Scraping

Data Observations

There are four main fields in the food.gov.uk search results :

Each entry could be a single product or multiple products, it is not always obvious from the description which is which.

Clicking into a result presents an opportunity to scrape more product information, however there is no consistent format in how products are presented, some had product content in paragraphs with
breaks, some has product content in html tables. This means alerts with multiple products will have to edited by hand.

Column Non-Null Count Dtype Notes
Source 748 non-null object Where data was sourced, food.gov.uk or nationalarchives.gov.uk
Date 748 non-null object Date the notice was issued
Alert_Type 748 non-null object Allergen or Safety Alert
Title 748 non-null object Alert Title Text
BodyText 748 non-null object Alert Body text (usually has more information)
usage: 44.0+ KB None

Engineered Features

Following on from Exploratory Data Analysis, Data Cleansing and Feature Engineering the data structure has been supplemented with additional fields for analysis.

Column Non-Null Count Dtype Engineered Feature Notes
Date 751 non-null datetime64[ns] Datetime conversion
datetime 751 non-null datetime64[ns] None
year 751 non-null int64 Datetime conversion
month 751 non-null object Datetime conversion
Alert_Type 751 non-null object None
Product_category 751 non-null object Edited by hand
Product_Type 751 non-null object Edited by hand
Title 751 non-null object None
BodyText 751 non-null object None
Supplier 751 non-null object Extract from Title or Body text
Product 751 non-null object Extract from Title or Body text
Risk 751 non-null object Extract from Title or Body text
Pathogen 191 non-null object Extract from Title or Body text
Allergen 269 non-null object Extract from Title or Body text
Foreign_Material 159 non-null object Extract from Title or Body text
Other 131 non-null object Extract from Title or Body text
month_num 751 non-null int32 Datetime conversion
month_name 751 non-null object Datetime conversion
year_month 751 non-null object Datetime conversion
datetime64[ns](2), int32(1), int64(1), object(15)
usage: 108.7+ KB None