Lecture notes Definition of Data science

First, let's start with a definition of data science from the chapter:




"Data science is the extraction of actionable knowledge from noisy data using scientific methods."




This definition highlights the three key components of data science: noisy data, scientific methods, and actionable knowledge. In the videos, we
see these components in action as we explore the concept of data preprocessing and learn how to clean and prepare data for analysis.




For example, in one of the videos, we are given a dataset of NBA player statistics and asked to predict which players are most likely to be
successful in the league. However, before we can do any analysis, we need to clean and preprocess the data. This involves removing missing
values, handling outliers, and transforming the data into a format that is suitable for analysis.




Here is an example of how we might remove missing values from the dataset using Python:

, import pandas as pd




# Load the dataset


data = pd.read_csv('nba_stats.csv')




# Remove any rows with missing values


data.dropna(inplace=True)


According to the chapter, this process of cleaning and preprocessing data is essential for successful data analysis because it allows us to
extract actionable knowledge from noisy data. As the author states:




"Without preprocessing, data is often too noisy and irregular to be of much use."