pandas DataFrame (2d)

import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
import seaborn as sns

DataFrame from historal rates data

df = pd.read_csv('rates.csv', parse_dates=['Time']) # wrong, dates are not ordered correctly
df.index = df['Time']
df.head()

	Time	USD	JPY	BGN	CZK	DKK	GBP	CHF
Time
2024-01-17	2024-01-17	1.0877	160.65	1.9558	24.755	7.4586	0.85818	0.9406
2024-01-16	2024-01-16	1.0882	159.64	1.9558	24.710	7.4582	0.86078	0.9361
2024-01-15	2024-01-15	1.0945	159.67	1.9558	24.714	7.4590	0.86075	0.9351
2024-01-12	2024-01-12	1.0942	159.17	1.9558	24.689	7.4565	0.85950	0.9350
2024-01-11	2024-01-11	1.0987	159.71	1.9558	24.659	7.4568	0.86145	0.9338

df.dtypes

Time    datetime64[ns]
USD            float64
JPY            float64
BGN            float64
CZK            float64
DKK            float64
GBP            float64
CHF            float64
dtype: object

df.index  # RangeIndex, enumerates the rows

DatetimeIndex(['2024-01-17', '2024-01-16', '2024-01-15', '2024-01-12',
               '2024-01-11', '2024-01-10', '2024-01-09', '2024-01-08',
               '2024-01-05', '2024-01-04', '2024-01-03', '2024-01-02',
               '2023-12-29', '2023-12-28', '2023-12-27', '2023-12-22',
               '2023-12-21', '2023-12-20', '2023-12-19', '2023-12-18',
               '2023-12-15', '2023-12-14', '2023-12-13', '2023-12-12',
               '2023-12-11', '2023-12-08', '2023-12-07', '2023-12-06',
               '2023-12-05', '2023-12-04', '2023-12-01', '2023-11-30',
               '2023-11-29', '2023-11-28', '2023-11-27', '2023-11-24',
               '2023-11-23', '2023-11-22', '2023-11-21', '2023-11-20',
               '2023-11-17', '2023-11-16', '2023-11-15', '2023-11-14',
               '2023-11-13', '2023-11-10', '2023-11-09', '2023-11-08',
               '2023-11-07', '2023-11-06', '2023-11-03', '2023-11-02',
               '2023-11-01', '2023-10-31', '2023-10-30', '2023-10-27',
               '2023-10-26', '2023-10-25', '2023-10-24', '2023-10-23',
               '2023-10-20'],
              dtype='datetime64[ns]', name='Time', freq=None)

df.index = df['Time']
df.index

DatetimeIndex(['2024-01-17', '2024-01-16', '2024-01-15', '2024-01-12',
               '2024-01-11', '2024-01-10', '2024-01-09', '2024-01-08',
               '2024-01-05', '2024-01-04', '2024-01-03', '2024-01-02',
               '2023-12-29', '2023-12-28', '2023-12-27', '2023-12-22',
               '2023-12-21', '2023-12-20', '2023-12-19', '2023-12-18',
               '2023-12-15', '2023-12-14', '2023-12-13', '2023-12-12',
               '2023-12-11', '2023-12-08', '2023-12-07', '2023-12-06',
               '2023-12-05', '2023-12-04', '2023-12-01', '2023-11-30',
               '2023-11-29', '2023-11-28', '2023-11-27', '2023-11-24',
               '2023-11-23', '2023-11-22', '2023-11-21', '2023-11-20',
               '2023-11-17', '2023-11-16', '2023-11-15', '2023-11-14',
               '2023-11-13', '2023-11-10', '2023-11-09', '2023-11-08',
               '2023-11-07', '2023-11-06', '2023-11-03', '2023-11-02',
               '2023-11-01', '2023-10-31', '2023-10-30', '2023-10-27',
               '2023-10-26', '2023-10-25', '2023-10-24', '2023-10-23',
               '2023-10-20'],
              dtype='datetime64[ns]', name='Time', freq=None)

df

	Time	USD	JPY	BGN	CZK	DKK	GBP	CHF
Time
2024-01-17	2024-01-17	1.0877	160.65	1.9558	24.755	7.4586	0.85818	0.9406
2024-01-16	2024-01-16	1.0882	159.64	1.9558	24.710	7.4582	0.86078	0.9361
2024-01-15	2024-01-15	1.0945	159.67	1.9558	24.714	7.4590	0.86075	0.9351
2024-01-12	2024-01-12	1.0942	159.17	1.9558	24.689	7.4565	0.85950	0.9350
2024-01-11	2024-01-11	1.0987	159.71	1.9558	24.659	7.4568	0.86145	0.9338
...	...	...	...	...	...	...	...	...
2023-10-26	2023-10-26	1.0540	158.48	1.9558	24.714	7.4632	0.87170	0.9466
2023-10-25	2023-10-25	1.0576	158.55	1.9558	24.693	7.4639	0.87240	0.9474
2023-10-24	2023-10-24	1.0632	159.26	1.9558	24.659	7.4648	0.87025	0.9501
2023-10-23	2023-10-23	1.0597	158.91	1.9558	24.645	7.4634	0.87153	0.9461
2023-10-20	2023-10-20	1.0591	158.80	1.9558	24.704	7.4620	0.87213	0.9442

61 rows × 8 columns

df.shape

(61, 8)

Selecting/dropping columns

df
df_dropped = df.drop(columns=['Time', 'BGN', 'DKK', 'CZK'])
df_dropped.head()

	USD	JPY	GBP	CHF
Time
2024-01-17	1.0877	160.65	0.85818	0.9406
2024-01-16	1.0882	159.64	0.86078	0.9361
2024-01-15	1.0945	159.67	0.86075	0.9351
2024-01-12	1.0942	159.17	0.85950	0.9350
2024-01-11	1.0987	159.71	0.86145	0.9338

df.head() # original df unaffected

	Time	USD	JPY	BGN	CZK	DKK	GBP	CHF
Time
2024-01-17	2024-01-17	1.0877	160.65	1.9558	24.755	7.4586	0.85818	0.9406
2024-01-16	2024-01-16	1.0882	159.64	1.9558	24.710	7.4582	0.86078	0.9361
2024-01-15	2024-01-15	1.0945	159.67	1.9558	24.714	7.4590	0.86075	0.9351
2024-01-12	2024-01-12	1.0942	159.17	1.9558	24.689	7.4565	0.85950	0.9350
2024-01-11	2024-01-11	1.0987	159.71	1.9558	24.659	7.4568	0.86145	0.9338

# Using a boolean mask to select columns
df.columns != 'Time'

array([False,  True,  True,  True,  True,  True,  True,  True])

df_dropped2 = df.loc[:, df.columns != 'Time']
df_dropped2

	USD	JPY	BGN	CZK	DKK	GBP	CHF
Time
2024-01-17	1.0877	160.65	1.9558	24.755	7.4586	0.85818	0.9406
2024-01-16	1.0882	159.64	1.9558	24.710	7.4582	0.86078	0.9361
2024-01-15	1.0945	159.67	1.9558	24.714	7.4590	0.86075	0.9351
2024-01-12	1.0942	159.17	1.9558	24.689	7.4565	0.85950	0.9350
2024-01-11	1.0987	159.71	1.9558	24.659	7.4568	0.86145	0.9338
...	...	...	...	...	...	...	...
2023-10-26	1.0540	158.48	1.9558	24.714	7.4632	0.87170	0.9466
2023-10-25	1.0576	158.55	1.9558	24.693	7.4639	0.87240	0.9474
2023-10-24	1.0632	159.26	1.9558	24.659	7.4648	0.87025	0.9501
2023-10-23	1.0597	158.91	1.9558	24.645	7.4634	0.87153	0.9461
2023-10-20	1.0591	158.80	1.9558	24.704	7.4620	0.87213	0.9442

61 rows × 7 columns

# Dropping several columns
df_dropped3 = df.drop(columns=['CZK', 'USD', 'Time'])
df_dropped3.head()

	JPY	BGN	DKK	GBP	CHF
Time
2024-01-17	160.65	1.9558	7.4586	0.85818	0.9406
2024-01-16	159.64	1.9558	7.4582	0.86078	0.9361
2024-01-15	159.67	1.9558	7.4590	0.86075	0.9351
2024-01-12	159.17	1.9558	7.4565	0.85950	0.9350
2024-01-11	159.71	1.9558	7.4568	0.86145	0.9338