Camping at Datacamp - Next

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

returns = pd.read_excel('07-22_VN_IND_PCTCHANGE.xlsx')
returns.set_index('Date', inplace=True)

###Return Monthly
print(returns.head())

macre_int = pd.read_excel('VN_Macro_Data.xlsx', sheet_name='MACRE')
macre_int.rename(columns={'QID': 'Date'}, inplace=True)
macre_int.set_index('Date', inplace=True)

###Macro Data
macre_int

#period_1 in range(0,21)
#period_2 in range(22,41)
#period_3 in range(42,53)
#period_4 in range(43,64)

import seaborn as sns

corr = macre_int.corr()
corr

import matplotlib.pyplot as plt

# Set figure size and DPI
plt.figure(figsize=(10, 8), dpi=1800)

# Plot heatmap of correlation matrix
sns.heatmap(corr, annot=True, annot_kws={"size": 5})
plt.yticks(rotation=0, size=5)
plt.xticks(rotation=90, size=5)
plt.tight_layout()
plt.show()

vif_test = macre_int.drop(["VNGOVBY_1Y", "deposit_rate", "lending_rate", 
                          "policy_rate","quar_crg", "gcpi",
                          "IND_ewma", "CD_ewma"], axis=1)
vif_test

from statsmodels.stats.outliers_influence import variance_inflation_factor 

# the independent variables set 
X = vif_test

# VIF dataframe 
vif_data = pd.DataFrame() 
vif_data["feature"] = X.columns 

# calculating VIF for each feature 
vif_data["VIF"] = [variance_inflation_factor(X.values, i) 
						for i in range(len(X.columns))] 

print(vif_data)