Tedilte Abraham/

Course Notes: Joining Data with pandas


Course Notes

Use this workspace to take notes, store code snippets, or build your own interactive cheatsheet! The datasets used in this course are available in the datasets folder.

# Use melt on ten_yr, unpivot everything besides the metric column
bond_perc = ten_yr.melt(id_vars=['metric'], var_name=['date'], value_name='close')

# Use query on bond_perc to select only the rows where metric=close
bond_perc_close = bond_perc.query('metric== "close"')

# Merge (ordered) dji and bond_perc_close on date with an inner join
dow_bond = pd.merge_ordered(dji, bond_perc_close, on='date', how='inner', suffixes=('_dow', '_bond'))

# Plot only the close_dow and close_bond columns
dow_bond.plot(x='date', y=['close_dow', 'close_bond'], rot=90)
# unpivot everything besides the year column
ur_tall = ur_wide.melt(id_vars=['year'], var_name=['month'], value_name='unempl_rate')

# Create a date column using the month and year columns of ur_tall
ur_tall['date'] = pd.to_datetime(ur_tall['year'] + '-' + ur_tall['month'])

# Sort ur_tall by date in ascending order
ur_sorted = ur_tall.sort_values(by='date')

# Plot the unempl_rate by date
ur_sorted.plot(x='date', y='unempl_rate')
# Use merge_asof() to merge jpm and wells
jpm_wells = pd.merge_asof(jpm, wells, on='date_time', 
                          suffixes=('', '_wells'), direction='nearest')

# Use merge_asof() to merge jpm_wells and bac
jpm_wells_bac = pd.merge_asof(jpm_wells, bac, on='date_time', 
                              suffixes=('_jpm', '_bac'), direction='nearest')

# Compute price diff
price_diffs = jpm_wells_bac.diff()

# Plot the price diff of the close of jpm, wells and bac only
# Merge gdp and pop on country and date with fill
date_ctry = pd.merge_ordered(gdp, pop, on=['country', 'date'], fill_method='ffill')

# Print date_ctry
# Use merge_ordered() to merge inflation, unemployment with inner join
inflation_unemploy = pd.merge_ordered(inflation, unemployment, on='date', how='inner')

# Print inflation_unemploy 

# Plot a scatter plot of unemployment_rate vs cpi of inflation_unemploy
inflation_unemploy.plot(x='unemployment_rate', y='cpi', kind='scatter')
gdp_sp500 = pd.merge_ordered(gdp, sp500, left_on='year', right_on='date', 
                             how='left',  fill_method='ffill')

# Subset the gdp and returns columns
gdp_returns = gdp_sp500[['gdp', 'returns']]

# Print gdp_returns correlation
print (gdp_returns.corr())
Run cancelled
# Concatenate the tracks, show only columns names that are in all tables
tracks_from_albums = pd.concat([tracks_master,tracks_ride, tracks_st],
Run cancelled
# Merge the non_mus_tck and top_invoices tables on tid
tracks_invoices = non_mus_tcks.merge(top_invoices, on='tid', how='inner')

# Use .isin() to subset non_mus_tcks to rows with tid in tracks_invoices
top_tracks = non_mus_tcks[non_mus_tcks['tid'].isin(tracks_invoices['tid'])]

# Group the top_tracks by gid and count the tid rows
cnt_by_gid = top_tracks.groupby(['gid'], as_index=False).agg({'tid':'count'})

# Merge the genres table to cnt_by_gid on gid and print
print(cnt_by_gid.merge(genres, on='gid'))
Run cancelled
# Merge employees and top_cust
empl_cust = employees.merge(top_cust, on='srid', 
                                 how='left', indicator=True)

# Select the srid column where _merge is left_only
srid_list = empl_cust.loc[empl_cust['_merge'] == 'left_only', 'srid']

# Get employees not working with top customers
Run cancelled
orig_seq = sequels_fin.merge(sequels_fin, how='inner', left_on='sequel', 
                             right_on='id', right_index=True,

# Add calculation to subtract revenue_org from revenue_seq 
orig_seq['diff'] = orig_seq['revenue_seq'] - orig_seq['revenue_org']

# Select the title_org, title_seq, and diff 
titles_diff = orig_seq[['title_org','title_seq','diff']]

# Print the first rows of the sorted titles_diff
print(titles_diff.sort_values('diff', ascending=False).head())
Run cancelled
# Import any packages you want to use here
Run cancelled
# Merge to the movies table the ratings table on the index
movies_ratings = movies.merge(ratings,on=['id'])

# Print the first few rows of movies_ratings
Unknown integration
DataFrameavailable as
Run cancelled
Join … using .merge

# Merge the taxi_owners and taxi_veh tables setting a suffix
taxi_own_veh = taxi_owners.merge(taxi_veh, on='vid', suffixes=('_own','_veh'))

# Print the value_counts to find the most popular fuel_type

# Merge the licenses and biz_owners table on account
licenses_owners = licenses.merge(biz_owners, on='account')

# Group the results by title then count the number of accounts
counted_df = licenses_owners.groupby('title').agg({'account':'count'})

# Sort the counted_df in desending order
sorted_df = counted_df.sort_values('account', ascending=False)

# Use .head() method to print the first few rows of sorted_df

# Merge the ridership, cal, and stations tables
ridership_cal_stations = ridership.merge(cal, on=['year','month','day']) \
                            .merge(stations, on='station_id')

# Create a filter to filter ridership_cal_stations
filter_criteria = ((ridership_cal_stations['month'] == 7) 
                   & (ridership_cal_stations['day_type'] == 'Weekday') 
                   & (ridership_cal_stations['station_name'] == 'Wilson'))

# Use .loc and the filter to select for rides
print(ridership_cal_stations.loc[filter_criteria, 'rides'].sum())

# Merge licenses and zip_demo, on zip; and merge the wards on ward
licenses_zip_ward = licenses.merge(zip_demo, on='zip') \
.merge(wards, on='ward')

# Print the results by alderman and show median income

# Merge land_use and census and merge result with licenses including suffixes
land_cen_lic = land_use.merge(census, on='ward') \
                    .merge(licenses, on='ward', suffixes=('_cen','_lic'))

# Group by ward, pop_2010, and vacant, then count the # of accounts
pop_vac_lic = land_cen_lic.groupby(['ward','pop_2010','vacant'], 

# Sort pop_vac_lic and print the results
sorted_pop_vac_lic = pop_vac_lic.sort_values(['vacant', 'account', 'pop_2010'], ascending=[False, True, True])

# Print the top few rows of sorted_pop_vac_lic
This query is taking long to finish...Consider adding a LIMIT clause or switching to Query mode to preview the result.

  • AI Chat
  • Code