Lära Types of Sports Data | Introduction to Sports Analytics

Sports data comes in many forms, but it is often categorized as either structured or unstructured. Structured data is organized in a clear, tabular format, making it easy to analyze. In sports, structured data includes player statistics such as points scored, assists, rebounds, minutes played, and other quantifiable metrics. Unstructured data, on the other hand, does not follow a predefined data model. Examples in sports might include video footage of matches, audio commentary, social media posts, or free-text scouting reports.

For instance, a basketball player's game-by-game statistics stored in a spreadsheet or database is structured data. The same player's highlight video or a coach's spoken feedback about their performance would be unstructured data. Both types are valuable for sports analytics, but structured data is typically the starting point for most analyses because it is easier to manipulate and visualize using tools like pandas.


              12345678910111213
            
import pandas as pd

# Create a DataFrame for player statistics
data = {
    "Player": ["Alex Smith", "Jordan Lee", "Taylor Kim"],
    "Points": [22, 15, 18],
    "Assists": [5, 7, 4],
    "Rebounds": [10, 8, 9],
    "Minutes": [34, 28, 30]
}

player_stats_df = pd.DataFrame(data)
print(player_stats_df)

A DataFrame is a two-dimensional, tabular data structure provided by the pandas library. It is similar to a spreadsheet or a SQL table. In the example above, each row represents a player and each column represents a statistic such as points, assists, rebounds, or minutes played. This structure allows you to easily access, filter, and analyze the data, which is why DataFrames are widely used in sports analytics to represent structured data.


              1234567891011
            
import pandas as pd

# Create a DataFrame for match event logs
event_data = {
    "Minute": [5, 17, 23, 41],
    "Player": ["Alex Smith", "Jordan Lee", "Taylor Kim", "Alex Smith"],
    "Event": ["Goal", "Foul", "Assist", "Yellow Card"]
}

event_logs_df = pd.DataFrame(event_data)
print(event_logs_df)

Var allt tydligt?

Tack för dina kommentarer!

Avsnitt 1. Kapitel 2

Fråga AI

Fråga vad du vill eller prova någon av de föreslagna frågorna för att starta vårt samtal

Suggested prompts:

Can you explain more about how event logs are used in sports analytics?

What are some examples of unstructured data in sports besides video and audio?

How can I analyze player statistics using pandas DataFrames?

Svep för att visa menyn


              12345678910111213
            
import pandas as pd

# Create a DataFrame for player statistics
data = {
    "Player": ["Alex Smith", "Jordan Lee", "Taylor Kim"],
    "Points": [22, 15, 18],
    "Assists": [5, 7, 4],
    "Rebounds": [10, 8, 9],
    "Minutes": [34, 28, 30]
}

player_stats_df = pd.DataFrame(data)
print(player_stats_df)


              1234567891011
            
import pandas as pd

# Create a DataFrame for match event logs
event_data = {
    "Minute": [5, 17, 23, 41],
    "Player": ["Alex Smith", "Jordan Lee", "Taylor Kim", "Alex Smith"],
    "Event": ["Goal", "Foul", "Assist", "Yellow Card"]
}

event_logs_df = pd.DataFrame(event_data)
print(event_logs_df)

Var allt tydligt?

Tack för dina kommentarer!

Avsnitt 1. Kapitel 2