# Groupby method
# split the data into groups based on some criteria
# calculate statistics or apply a function to each group
# group data using rank
df_rank = df.groupby(['rank'])

# Calculate mean value for each numneric column per each group
df_rank.mean()

# Calculate mean salary for each professor rank
df.groupby('rank')[['salary']].mean()

# groupby performance notes:
#   - no grouping/splitting occurs unit it's needed. Creating the groupby object only verifies that you have passed a valid mapping
#   - by default, the group keys are sorted during the groupby operation. You may want to pass sort=false for potential speedup
# Calculate mean salary for each professor rank:
df.groupby(['rank'],sort=False)[['salary']].mean()

# FILTERING
# Calculate salary greater than 120000
df_sub = df[df['salary']>120000]
print(df_sub)

# Select only those rows that contain female professors:
df_f = df[df['sex']=='Female']
print(df_f)