Week 7 - data analysis

what does data analysis allow for

problem solving, hypothesis testing and evidence-based decision making

data analysis in python

open source so broad tool, make dealing with large data sets easier,

pandas

• data frame object for data manipulation

DataFrame

a common form data is stored in, a table which contains many different datatypes such as integers, strings, floats and lists

df.head()

prints first few rows of data

df.info()

shows you the columns, if they have nukk data and variable type of each column

df.shape()

will give you the size of the data (number of rows x columns)

.mean()

average of each column

.std()

standard deviation of each column

.unique()

gives u unique values in that column

seaborn

integrates with pandas

• has large number of plotting functions

• default plotting parameters look good

• easy to customise