plot aggregate pandas data

number = 1_000_000.50
f"${number:,.0f}"
'$1,000,000'

f"${number:,.2f}"
'$1,000,000.50'

# Pre-defined lists
names = ['United States', 'Australia', 'Japan', 'India', 'Russia', 'Morocco', 'Egypt']
dr =  [True, False, False, False, True, True, True]
cpc = [809, 731, 588, 18, 200, 70, 45]

# Import pandas as pd
import pandas as pd

# Create dictionary my_dict with three key:value pairs: my_dict
my_dict = {'country':['United States', 'Australia', 'Japan', 'India', 'Russia', 'Morocco', 'Egypt'],
'drives_right':[True, False, False, False, True, True, True],
'cars_per_cap':[809, 731, 588, 18, 200, 70, 45]}

# Build a DataFrame cars from my_dict: cars
cars = pd.DataFrame(my_dict)

# Print cars
print(cars)



#Now this is indexed beautiful arrangement of data
import pandas as pd

# Build cars DataFrame
names = ['United States', 'Australia', 'Japan', 'India', 'Russia', 'Morocco', 'Egypt']
dr =  [True, False, False, False, True, True, True]
cpc = [809, 731, 588, 18, 200, 70, 45]
cars_dict = { 'country':names, 'drives_right':dr, 'cars_per_cap':cpc }
cars = pd.DataFrame(cars_dict)
print(cars)

# Definition of row_labels
row_labels = ['US', 'AUS', 'JPN', 'IN', 'RU', 'MOR', 'EG']

# Specify row labels of cars
cars.index = row_labels

# Print cars again
print(cars)

# Import pandas as pd
import pandas as pd

# Fix import by including index_col
cars = pd.read_csv('cars.csv', index_col = 0)

# Print out cars
print(cars)

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

# Print out country column as Pandas Series
print(cars['country'])

# Print out country column as Pandas DataFrame
print(cars[['country']])


# Print out DataFrame with country and drives_right columns
print(cars[['country','drives_right']])

# 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]])

# 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]])

# 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

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)

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()

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

import pandas as pd
from tqdm import tqdm
from datasets import load_dataset

def download_n_eb_articles(n: int) -> pd.DataFrame:
    """Extract n Ekstra Bladet articles from the Danish subset
    of the mC4 dataset.
    Args:
        n (int): Number of articles to extract.
    Returns:
        pd.DataFrame: Ekstra Bladet articles.
    """
    
    mc4 = load_dataset("mc4", "da", streaming=True)
    i, docs = 0, []
    
    with tqdm(total=n) as pbar:
      
        for doc in mc4["train"]:
          
            if "ekstrabladet.dk" in doc["url"]:
            
                docs.append(doc)
                i += 1
                pbar.update(1)
                
                if i == n:
                    break
                    
    return pd.DataFrame(docs)
@kasperjunge

a_json = raw_json['daily']

df = pd.DataFrame.from_dict(a_json)
df['time'] = pd.to_datetime(df['time'], format='%Y-%m-%d')

df.info()