Understanding statistical description

Running describe method shows us the statistical information about the attributes(columns). It tells us about-

count- It tells us about the count of total non-null values present in a particular column. So, as we can see longitude has 20640 non-null values but total_bedrooms have only 20433 non-null values.
mean- It tells us about the average or mean value of the column.
std- It tells us about the standard deviation of the column. We'll talk about it in next slides.
min- The minimum value in a column.
25%, 50% and 75%- These are percentiles(25th percentile, 50th percentile and 75th percentile). So, 25% or 25th percentile of housing_median_age is 18 and 75th percentile is 37. That means 25% of the instances of housing_median_age have value less than 18 and 75% of the instances have value less than 37.
max- The maximum value in a column

Loading comments...