SESIÓN 2. Introducción a Series de Tiempo en Python

Autor/a

Gerson Rivera

Fecha de publicación

15 agosto 2024

Importar los paquetes

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
sns.set()

Importando la base de datos

raw_csv_data = pd.read_csv("Index2018.csv")
df_comp = raw_csv_data.copy()

Análisis Exploratorio

df_comp.head(10)
date spx dax ftse nikkei
0 07/01/1994 469.90 2224.95 3445.98 18124.01
1 10/01/1994 475.27 2225.00 3440.58 18443.44
2 11/01/1994 474.13 2228.10 3413.77 18485.25
3 12/01/1994 474.17 2182.06 3372.02 18793.88
4 13/01/1994 472.47 2142.37 3360.01 18577.26
5 14/01/1994 474.91 2151.05 3400.56 18973.70
6 17/01/1994 473.30 2115.56 3407.83 18725.37
7 18/01/1994 474.25 2130.35 3437.01 18514.55
8 19/01/1994 474.30 2132.52 3475.15 19039.40
9 20/01/1994 474.98 2098.36 3469.99 19183.92 
df_comp
date spx dax ftse nikkei
0 07/01/1994 469.900000 2224.95 3445.980000 18124.01
1 10/01/1994 475.270000 2225.00 3440.580000 18443.44
2 11/01/1994 474.130000 2228.10 3413.770000 18485.25
3 12/01/1994 474.170000 2182.06 3372.020000 18793.88
4 13/01/1994 472.470000 2142.37 3360.010000 18577.26
... ... ... ... ... ...
6264 23/01/2018 2839.130362 13559.60 7731.827774 24124.15
6265 24/01/2018 2837.544008 13414.74 7643.428966 23940.78
6266 25/01/2018 2839.253031 13298.36 7615.839954 23669.49
6267 26/01/2018 2872.867839 13340.17 7665.541292 23631.88
6268 29/01/2018 2853.528411 13324.48 7671.533300 23629.34

6269 rows × 5 columns

df_comp.describe()
spx dax ftse nikkei
count 6269.000000 6269.000000 6269.000000 6269.000000
mean 1288.127542 6080.063363 5422.713545 14597.055700
std 487.586473 2754.361032 1145.572428 4043.122953
min 438.920000 1911.700000 2876.600000 7054.980000
25% 990.671905 4069.350000 4486.100000 10709.290000
50% 1233.420000 5773.340000 5662.430000 15028.170000
75% 1459.987747 7443.070000 6304.250000 17860.470000
max 2872.867839 13559.600000 7778.637689 24124.150000 
df_comp.isna()
date spx dax ftse nikkei
0 False False False False False
1 False False False False False
2 False False False False False
3 False False False False False
4 False False False False False
... ... ... ... ... ...
6264 False False False False False
6265 False False False False False
6266 False False False False False
6267 False False False False False
6268 False False False False False

6269 rows × 5 columns

df_comp.isna().sum()
date      0
spx       0
dax       0
ftse      0
nikkei    0
dtype: int64
df_comp.spx.isna().sum()
np.int64(0)
df_comp['spx'].isna().sum()
np.int64(0)

Construcción Gráfica

import matplotlib.pyplot as plt
df_comp.spx.plot(figsize=(20,5), title = "S&P500 Precios",color='green')
plt.legend()
plt.show()

df_comp['ftse'].plot(figsize=(20,5), title = "FTSE100 Prices",color='red')
plt.show()

df_comp.spx.plot(figsize=(20,5), title = "S&P500 Prices")
df_comp.ftse.plot(figsize=(20,5), title = "FTSE100 Prices")
plt.title("S&P vs FTSE")
plt.legend()
plt.show()

Gráficos QQ (The QQ Plot)

import scipy.stats
plt.figure(figsize=(20,6))
scipy.stats.probplot(df_comp['spx'], plot =  plt)

plt.title("QQ Plot", size = 40)
plt.show()