Pandas Series

#assign a value to a variable:
types_of_people = 10 
# make a string using variable name:
X = f “there are {types_of_people} types of people.”

Output:
There are 10 types of people

from pydantic import BaseModel, Field
from uuid import UUID, uuid4

class item(BaseModel):
    name : str
    price : float
    item_id : UUID = Field(default_factory = uuid4)


items = []

for i in range(3):
    items.append(item(name = 'test', price = 20))


print(items)

from cryptography.fernet import Fernet
import sqlite3

# Generate key to use it
#print(Fernet.generate_key())

key = b'rMqQ4gNSsvkubQnn9CmW25PTFDwNlQPUp7YN4qDVSts='
cipher_suite = Fernet(key)

db_name = 'mydb.db'

conn = sqlite3.connect(db_name)
cursor = conn.cursor()

# create a table
cursor.execute('create table if not exists items (name STRING, price INTEGER)')

def add_item(name, price):
    name = cipher_suite.encrypt(name.encode())
    price = cipher_suite.encrypt(str(price).encode())

    cursor.execute('insert into items (name, price) values (?, ?)', (name, price))

    conn.commit()

add_item('test', 50)

def get_items():
    results = cursor.execute('select * from items').fetchall()
    for item in results:
        name = cipher_suite.decrypt(item[0]).decode()
        price = cipher_suite.decrypt(item[1]).decode()
        print(name, price)

get_items()

for index, row in urls_df.head(2).iterrows():
    print(f"Fetchiing URL: {row['url']}")
    api_output = fetch_metadata(row['url'])
    
    urls_df.loc[index, 'title'] = api_output['title']
    urls_df.loc[index, 'description'] = api_output['site_name']
    
urls_df

import pandas as pd
dict = {"Population": {"Delhi":10927986, "Mumbai":12691836, "Kolkata":4631392, "Chennai":4328063}, 
        "Hospitals":{"Delhi":189, "Mumbai":208, "Kolkata":149, "Chennai":157},
        "Schools":{"Delhi":7916, "Mumbai":8508, "Kolkata":7226, "Chennai":7617}}
df = pd.DataFrame(dict)
print("Before Adding Column")
print(df)
print("-------------------------")

df["Students"]="12K"
print("After Adding Column Students")
print(df)
print("-------------------------")


df["Teachers"]=["10k", "20k", "30k", "40k"]
print("After Adding Column Teachers")
print(df)
print("-------------------------")

df.iat[3,3]="10000K"
df.at["Delhi","Schools"]=555555
print(df)
print("-----------------------------------")

df.loc["Agra"]=10
df.loc["Mathura"]=[10, 20,30, 40, 50]
print(df)

df.loc["Rohta",["Hospitals", "Schools"]]=20000
print(df)

del df["Hospitals"]

print(df)

df.loc["Agra",["Schools", "Students"]]=[1000000, 200000]
df.loc["Ajmer",["Schools", "Students"]]=[10541,5874125]
print(df)

print("-----------Bye----------------------")
'# print(df.index)
# print(df.columns)
# print(df.loc[["Delhi", "Mumbai"],["Students", "Teachers"]])

# x =' df.drop(["Mumbai", "Agra"], axis=0)
# y = df.drop(["Students", "Teachers"], axis=1)
# print(x)
# print(y)
# print(df)

# print("New DataFrame------------------------------------------")
# newdf = df.rename(index={"Delhi":"D"})
# print(newdf)
# print(df)
# print("Old Data Frame -----------------------------------------")
# df.rename(index={"Delhi":"D"}, inplace=True)
# print(df)


newdf=df.rename(columns={"Population":"P"})
print(newdf)
df.rename(columns={"Population":"P"}, inplace=True)
print(df)
df.rename(index={"Delhi":"Agra"}, columns={"Schools":"College"}, inplace=True)
print(df)

import pandas as pd
list1=[-10,-20,-30]
ser = pd.Series(list1)
print(ser*2)

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()