Анализ данных в pandas

import numpy as np
import pandas as pd

df = pd.DataFrame({
    'student': ['Aysel', 'Murad', 'Leyla', 'Elvin', 'Nigar'],
    'group': ['A', 'B', 'A', 'B', 'A'],
    'math': [91, np.nan, 85, 64, np.nan],
    'physics': [88, 72, np.nan, 70, 81],
})
print(df.isna().sum())
print(df['math'].mean(), df['math'].count())
print(df.dropna().shape)
filled = df.fillna({'math': df['math'].median(), 'physics': df['physics'].mean()})
print(filled)
print(np.nan == np.nan)

import pandas as pd

df = pd.DataFrame({
    'store': ['Baku', 'Baku', 'Ganja', 'Baku', 'Ganja', 'Ganja', 'Baku'],
    'category': ['Food', 'Drinks', 'Food', 'Food', 'Drinks', 'Food', 'Drinks'],
    'amount': [120.0, 45.5, 80.0, 99.5, 30.0, 64.0, 52.0],
})
print(df.groupby('store')['amount'].sum())
summary = df.groupby('store').agg(
    total=('amount', 'sum'),
    average=('amount', 'mean'),
    orders=('amount', 'size'),
)
print(summary.round(2))
print(df.groupby(['store', 'category'])['amount'].sum())
df['share'] = (df['amount'] / df.groupby('store')['amount'].transform('sum')).round(3)
print(df.head(3))

import pandas as pd

orders = pd.DataFrame({'order_id': [1, 2, 3, 4],
                       'customer_id': [10, 11, 10, 13],
                       'amount': [25.0, 40.0, 15.5, 60.0]})
customers = pd.DataFrame({'customer_id': [10, 11, 12],
                          'name': ['Aysel', 'Murad', 'Leyla']})
inner = orders.merge(customers, on='customer_id')
print(inner)
left = orders.merge(customers, on='customer_id', how='left')
print(left[['order_id', 'name']])
outer = orders.merge(customers, on='customer_id', how='outer', indicator=True)
print(outer[['customer_id', 'order_id', 'name', '_merge']])

import pandas as pd

df = pd.DataFrame({
    'store': ['Baku', 'Baku', 'Ganja', 'Baku', 'Ganja', 'Ganja', 'Baku'],
    'category': ['Food', 'Drinks', 'Food', 'Food', 'Drinks', 'Food', 'Drinks'],
    'amount': [120.0, 45.5, 80.0, 99.5, 30.0, 64.0, 52.0],
})
pt = df.pivot_table(index='store', columns='category', values='amount',
                    aggfunc='sum', fill_value=0, margins=True)
print(pt)
print(df.pivot_table(index='store', columns='category', values='amount', aggfunc='count'))

import numpy as np
import pandas as pd

df = pd.DataFrame({'code': ['BAK', 'GNJ', 'SMQ', 'BAK'], 'amount': [120.0, 45.5, 80.0, 30.0]})
df['city'] = df['code'].map({'BAK': 'Baku', 'GNJ': 'Ganja', 'SMQ': 'Sumgait'})
df['size_apply'] = df['amount'].apply(lambda x: 'large' if x >= 60 else 'small')
df['size_where'] = np.where(df['amount'] >= 60, 'large', 'small')
df['band'] = pd.cut(df['amount'], bins=[0, 50, 100, 200], labels=['low', 'mid', 'high'])
print(df)
print((df['size_apply'] == df['size_where']).all())

import pandas as pd

sales = pd.DataFrame({
    'date': ['2026-01-15', '2026-01-28', '2026-02-03', '2026-02-20', '2026-03-05', '2026-03-18'],
    'amount': [310.0, 275.5, 402.0, 350.0, 390.0, 441.5],
})
sales['date'] = pd.to_datetime(sales['date'])
sales['month'] = sales['date'].dt.to_period('M')
sales['weekday'] = sales['date'].dt.day_name()
print(sales)
print(sales.groupby('month')['amount'].sum())
print((sales['date'].max() - sales['date'].min()).days, 'days')

import io
import pandas as pd

sales_csv = '''date,store,product_id,qty
2026-01-05,Baku,1,30
2026-01-12,Ganja,2,25
2026-01-20,Baku,3,12
2026-02-02,Baku,1,34
2026-02-14,Ganja,3,18
2026-02-25,Ganja,1,20
2026-03-03,Baku,2,41
2026-03-15,Ganja,2,28
2026-03-28,Baku,3,15'''
products = pd.DataFrame({'product_id': [1, 2, 3], 'product': ['Tea', 'Coffee', 'Cake'],
                         'price': [4.5, 6.0, 12.0]})
sales = pd.read_csv(io.StringIO(sales_csv), parse_dates=['date'])
df = sales.merge(products, on='product_id', how='left', validate='many_to_one')
df['revenue'] = df['qty'] * df['price']
df['month'] = df['date'].dt.month
report = df.pivot_table(index='month', columns='store', values='revenue',
                        aggfunc='sum', fill_value=0)
report['total'] = report.sum(axis=1)
report['growth_%'] = report['total'].pct_change().mul(100).round(1)
print(report)
print(df.groupby('product')['revenue'].sum().sort_values(ascending=False))

import pandas as pd

expenses = pd.DataFrame({
    'person': ['Aysel', 'Murad', 'Aysel', 'Leyla', 'Murad', 'Aysel', 'Leyla'],
    'category': ['food', 'transport', 'books', 'food', 'food', 'food', 'books'],
    'amount': [12.5, 3.0, 25.0, 18.0, 9.5, 7.0, 14.0],
})
# 1) total per person (dict)
# 2) category with the largest total
# 3) number of expenses per person (dict)

import pandas as pd

orders = pd.DataFrame({'order_id': [1, 2, 3, 4, 5], 'customer_id': [1, 2, 1, 3, 4],
                       'amount': [30.0, 45.0, 20.0, 15.0, 50.0]})
customers = pd.DataFrame({'customer_id': [1, 2, 3], 'city': ['Baku', 'Ganja', 'Baku']})
# merge, fill missing cities, then print the two results