loc and iloc in Pandas

PHOTO

Thu Nov 25 2021 06:55:14 GMT+0000 (UTC)

Saved by @Sourabh ##dictionary ##pandas #defining_data_frame #csv #dataframe #square #bracket'

# Import cars data
import pandas as pd
cars = pd.read_csv('cars.csv', index_col = 0)

# Print out observation for Japan
print(cars.loc['JPN'])
print(cars.iloc[2])

# Print out observations for Australia and Egypt
print(cars.loc[['AUS','EG']])
print(cars.iloc[[1,6]])

COPY

With loc and iloc you can do practically any data selection operation on DataFrames you can think of. loc is label-based, which means that you have to specify rows and columns based on their row and column labels. iloc is integer index based, so you have to specify rows and columns by their integer index

Save snippets that work from anywhere online with our extensions

Comments

Pandas

@Sourabh

CSV to DataFrame (2) Square Bracket in Pandas loc and iloc in Pandas loc and iloc - part 3 Filter observations from a DataFrame based on boolean arrays: Part 1 Filter observations from a DataFrame based on boolean arrays: Part 2 Dataframe subsetting Loop over Dataframe - Pandas Loop over Dataframe - Pandas: Part 2 adding columns to pandas dataframe

##pandas ##python

find the percentage of missing values in pandas

percent_missing = df.isnull().sum() * 100 / len(df)
missing_value_df = pd.DataFrame({'column_name': df.columns,
                                 'percent_missing': percent_missing})

#python #pandas #dataframe

brondata naar pandas dataframe

def load_table_to_df(fp, **kwargs):

    if fp.endswith('.xls'):
        result_df = pd.read_excel(fp, **kwargs)
        
    elif fp.endswith('.xlsx'):
        result_df = pd.read_excel(fp, engine='openpyxl', **kwargs)
        
    elif fp.endswith('.csv') or fp.endswith('.txt'):
        result_df = pd.read_csv(fp, **kwargs)
        
    elif fp.endswith('.parquet'):
        result_df = pd.read_parquet(fp, **kwargs)
        
    else:
        return "Wrong file extension"

    print('     -->  Succesfully loaded {}'.format(fp))
    return result_df

#python #pandas #dataframe

Adding new column to a dataframe

lins = pd.Series(lines, name='img_path')
train_df = pd.concat([train_df, lins], axis=1)

##pandas ##plot

plot aggregate pandas data

def f(x):
    d={}
    d['conversion_rate'] = x.ORDER_PLACED.mean()
    d['n_orders'] = len(x)
    d['aov'] = x.TOTAL_PRICE_PTC.mean()
    return pd.Series(d, index=['conversion_rate','n_orders','aov'])

AGG_CITIES = {
    city: (df
           .query('CITY_PTC==@city')
           .groupby(['COUNTRY_CODE_PTC','CITY_PTC','FREIGHT_PERC_BIN'])
           .apply(f)
           .reset_index())
    for city in df.CITY_PTC.unique()
}

colors = plt.rcParams["axes.prop_cycle"]()
fig, axes = plt.subplots(ncols=2, nrows=2, sharex=True, sharey=True, figsize=(18, 12))

for ax, (city, vals) in zip(axes.ravel(), AGG_CITIES.items()):
    c = next(colors)["color"]
    ax.plot(vals.FREIGHT_PERC_BIN, vals.conversion_rate, color=c, alpha=0.3, label=city)
    ax.set_ylabel('CONVERSION RATE')
    ax.set_xlabel('FREIGHT_PERC_BIN')   
    ax.xaxis.set_tick_params(rotation=65)
#    ax.axvline(x=np.mean(vals), color=c, linestyle="--")
#    ax.axvline(x=0, color="black")
#    ax.set_xlim(-0.3, 0.3)
    ax.legend()

##pandas

pandas - Apply multiple functions to multiple groupby columns

def f(x):
    d = {}
    d['a_sum'] = x['a'].sum()
    d['a_max'] = x['a'].max()
    d['b_mean'] = x['b'].mean()
    d['c_d_prodsum'] = (x['c'] * x['d']).sum()
    return pd.Series(d, index=['a_sum', 'a_max', 'b_mean', 'c_d_prodsum'])

df.groupby('group').apply(f)

#list #forloop #for #loop ##dictionary

Dice Random no

# Numpy is imported, seed is set

# Starting step
step = 50
# Roll the dice
dice = np.random.randint(1,7)
# Finish the control construct
if dice <= 2 :
    step = step - 1
elif dice <= 5 :
    step = step + 1
else:
    step = step + np.random.randint(1,7)

# Print out dice and step
print(dice)
print(step)

#list #forloop #for #loop ##dictionary

Random Numbers

# Import numpy as np
import numpy as np

# Set the seed
np.random.seed(123)

# Generate and print random float
print(np.random.rand())

#Roll The Dice
# Import numpy and set seed
import numpy as np
np.random.seed(123)

# Use randint() to simulate a dice
print(np.random.randint(1,7))
# Use randint() again
print(np.random.randint(1,7))

#list #forloop #for #loop ##dictionary

adding columns to pandas dataframe

# Import cars data
import pandas as pd
cars = pd.read_csv('cars.csv', index_col = 0)

# Use .apply(str.upper)


cars['COUNTRY'] = cars['country'].apply(str.upper)
print(cars)

#list #forloop #for #loop ##dictionary

Loop over Dataframe - Pandas: Part 2

# Import cars data
import pandas as pd
cars = pd.read_csv('cars.csv', index_col = 0)

# Adapt for loop
for lab, row in cars.iterrows() :
    print(lab + ": " + str(row['cars_per_cap']))

#Something new

# Import cars data
import pandas as pd
cars = pd.read_csv('cars.csv', index_col = 0)

# Code for loop that adds COUNTRY column
for lab, row in cars.iterrows():
    cars.loc[lab,'COUNTRY'] = row['country'].upper()


# Print cars
print(cars)

#list #forloop #for #loop ##dictionary

Loop over Dataframe - Pandas

#Iterating over a Pandas DataFrame is typically done with the iterrows()
# Import cars data
import pandas as pd
cars = pd.read_csv('cars.csv', index_col = 0)

# Iterate over rows of cars
for lab,row in cars.iterrows():
    print(lab)
    print(row)

#list #forloop #for #loop ##dictionary

Loop over numpy array

# Import numpy as np

import numpy as np
#for x in my_array : #in 1D Numpy array
#for x in np.nditer(my_array) : #for 2D Numpy array

# For loop over np_height

for x in np_height:
    print(str(x) + " inches")

# For loop over np_baseball
for x in (np.nditer(np_baseball)):
    print(x)

#list #forloop #for #loop ##dictionary

Loop over dictionary

# Definition of dictionary
europe = {'spain':'madrid', 'france':'paris', 'germany':'berlin',
          'norway':'oslo', 'italy':'rome', 'poland':'warsaw', 'austria':'vienna' }
          
# Iterate over europe
for key, value in europe.items() :
    print('the capital of ' + str(key) + ' is ' + str(value))

##dictionary ##pandas #defining_data_frame #csv #dataframe #square #bracket'

loc and iloc - part 3

# Import cars data
import pandas as pd
cars = pd.read_csv('cars.csv', index_col = 0)

# Print out drives_right column as Series
print(cars.loc[:, 'drives_right'])
print(cars.iloc[:, 1])

# Print out drives_right column as DataFrame
print(cars.loc[:, ['drives_right']])
print(cars.iloc[:, [1]]) #[] square brackets are very sensitive here


# Print out cars_per_cap and drives_right as DataFrame
print(cars.loc[:, ['drives_right', 'cars_per_cap']])
print(cars.iloc[:, [0,2]]) #[] square brackets are very sensitive here

##dictionary ##pandas #defining_data_frame #csv #dataframe #square #bracket'

loc and iloc - part 2

# Import cars data
import pandas as pd
cars = pd.read_csv('cars.csv', index_col = 0)

# Print out drives_right value of Morocco
print(cars.loc[['MOR', 'drives_right']])

# Print sub-DataFrame
print(cars.iloc[[4,5], [1,2]])

##dictionary ##pandas #defining_data_frame #csv #dataframe #square #bracket'

loc and iloc in Pandas

# Import cars data
import pandas as pd
cars = pd.read_csv('cars.csv', index_col = 0)

# Print out observation for Japan
print(cars.loc['JPN'])
print(cars.iloc[2])

# Print out observations for Australia and Egypt
print(cars.loc[['AUS','EG']])
print(cars.iloc[[1,6]])

loc and iloc in Pandas

Save snippets that work from anywhere online with our extensions

Comments

More like this

Pandas

Browse more snippets >>

loc and iloc in Pandas

Save snippets that work from anywhere online with our extensions

Comments

More like this

Pandas

Browse more snippets >>

Embed code snippet