Macroeconomic Indicators Affecting Stock Market

# Macro economic indicators (mostly US) from the FRED database
# Detailed info on each indicator check on web: https://fred.stlouisfed.org/series/<indicator_name>
# DOC with the metrics and external exploratory Colab: https://docs.google.com/document/d/1Cf4C3Xz4_yitlzPaLEknHoDlw7KMXey4c49kZ7ucQEE/edit?usp=sharing

FRED_INDICATORS = ['GDP', 'GDPC1', 'GDPPOT', 'NYGDPMKTPCDWLD',         # 1. Growth
                   'CPIAUCSL', 'CPILFESL', 'GDPDEF',                   # 2. Prices and Inflation
                   'M1SL', 'WM1NS', 'WM2NS', 'M1V', 'M2V', 'WALCL',    # 3. Money Supply
                   'DFF', 'DTB3', 'DGS5', 'DGS10', 'DGS30', 'T5YIE',   # 4. Interest Rates
                   'T10YIE', 'T5YIFR', 'TEDRATE', 'DPRIME',            # 4. Interest Rates
                   'UNRATE', 'NROU', 'CIVPART', 'EMRATIO',             # 5. Employment
                   'UNEMPLOY', 'PAYEMS', 'MANEMP', 'ICSA', 'IC4WSA',   # 5. Employment
                   'CDSP', 'MDSP', 'FODSP', 'DSPIC96', 'PCE', 'PCEDG', # 6. Income and Expenditure
                   'PSAVERT', 'DSPI', 'RSXFS',                         # 6. Income and Expenditure
                   'INDPRO', 'TCU', 'HOUST', 'GPDI', 'CP', 'STLFSI2',  # 7. Other indicators
                   'DCOILWTICO', 'DTWEXAFEGS', 'DTWEXBGS',             # 7. Other indicators
                   'GFDEBTN', 'GFDEGDQ188S',                           # 8. Gov-t debt
                   # 9. Additional indicators from IVAN
                   'DEXUSEU', 'GVZCLS', 'VIXCLS', 'DIVIDEND',
                   # 9. Additional indicators from IVAN
                   'MORTGAGE30US', 'SPCS20RSA'
                   ]

# Macro Indicators from QUANDL
QUANDL_INDICATORS = {'BCHAIN/MKPRU', 'USTREASURY/YIELD', 'USTREASURY/REALYIELD',  # 9. Additional indicators from IVAN
                     # 9. Additional indicators from IVAN
                     'MULTPL/SHILLER_PE_RATIO_MONTH', 'LBMA/GOLD'
                     }

# Stock maret indexes
  # All indexes: https://stooq.com/t/ 
STOOQ_INDICATORS = {'^DJI','^SPX'}  

for i,value in enumerate(macro_indicators.keys()):
  if i%6==0:
    print('\n')
  print(value, end =", ")  

# OUTPUT:
# GDP, GDPC1, GDPPOT, NYGDPMKTPCDWLD, CPIAUCSL, CPILFESL, 
# GDPDEF, M1SL, WM1NS, WM2NS, M1V, M2V, 
# WALCL, DFF, DTB3, DGS5, DGS10, DGS30, 
# T5YIE, T10YIE, T5YIFR, TEDRATE, DPRIME, UNRATE, 
# NROU, CIVPART, EMRATIO, UNEMPLOY, PAYEMS, MANEMP, 
# ICSA, IC4WSA, CDSP, MDSP, FODSP, DSPIC96, 
# PCE, PCEDG, PSAVERT, DSPI, RSXFS, INDPRO, 
# TCU, HOUST, GPDI, CP, STLFSI2, DCOILWTICO, 
# DTWEXAFEGS, DTWEXBGS, GFDEBTN, GFDEGDQ188S, DEXUSEU, GVZCLS, 
# VIXCLS, DIVIDEND, MORTGAGE30US, SPCS20RSA, BCHAIN_MKPRU, USTREASURY_YIELD, 
# MULTPL_SHILLER_PE_RATIO_MONTH, USTREASURY_REALYIELD, LBMA_GOLD, SPX, DJI, 

i=1
for value in macro_df.keys():
  if not ('future' in value):
    print(value, end =", ")
    if i%8==0:
      print('\n')
    i+=1

# OUTPUT:
# WM1NS_wow, WM1NS_mom, WM2NS_wow, WM2NS_mom, WALCL_wow, WALCL_mom, DFF, DTB3, 
# DGS5, DGS10, DGS30, T5YIE, T10YIE, T5YIFR, TEDRATE, DPRIME, 
# ICSA_wow, ICSA_mom, IC4WSA_wow, IC4WSA_mom, STLFSI2, STLFSI2_wow, STLFSI2_mom, DCOILWTICO, 
# DCOILWTICO_growth_1d, DCOILWTICO_growth_3d, DCOILWTICO_growth_7d, 
# DCOILWTICO_growth_30d, DCOILWTICO_growth_90d, DCOILWTICO_growth_365d, DTWEXAFEGS, DTWEXBGS, 
# DEXUSEU, GVZCLS, VIXCLS, MORTGAGE30US, MORTGAGE30US_wow, MORTGAGE30US_mom, BCHAIN_MKPRU, BCHAIN_MKPRU_growth_1d, 
# BCHAIN_MKPRU_growth_3d, BCHAIN_MKPRU_growth_7d, BCHAIN_MKPRU_growth_30d, BCHAIN_MKPRU_growth_90d, BCHAIN_MKPRU_growth_365d, LBMA_GOLD, LBMA_GOLD_growth_1d, LBMA_GOLD_growth_3d, 
# LBMA_GOLD_growth_7d, LBMA_GOLD_growth_30d, LBMA_GOLD_growth_90d, LBMA_GOLD_growth_365d, SPX, SPX_growth_1d, SPX_growth_3d, SPX_growth_7d, 
# SPX_growth_30d, SPX_growth_90d, SPX_growth_365d, DJI, DJI_growth_1d, DJI_growth_3d, DJI_growth_7d, DJI_growth_30d, 
# DJI_growth_90d, DJI_growth_365d, GDP_qoq, GDP_yoy, GDPC1_qoq, GDPC1_yoy, GDPPOT_qoq, GDPPOT_yoy, 
# NYGDPMKTPCDWLD_yoy, CPIAUCSL_mom, CPIAUCSL_yoy, CPILFESL_mom, CPILFESL_yoy, GDPDEF, GDPDEF_qoq, GDPDEF_yoy, 
# M1SL_mom, M1SL_yoy, M1V, M1V_qoq, M1V_yoy, M2V, M2V_qoq, M2V_yoy, 
# UNRATE, UNRATE_mom, UNRATE_yoy, NROU, NROU_qoq, NROU_yoy, CIVPART, CIVPART_mom, 
# CIVPART_yoy, EMRATIO, EMRATIO_mom, EMRATIO_yoy, UNEMPLOY_mom, UNEMPLOY_yoy, PAYEMS_mom, PAYEMS_yoy, 
# MANEMP_mom, MANEMP_yoy, CDSP, CDSP_qoq, CDSP_yoy, MDSP, MDSP_qoq, MDSP_yoy, 
# FODSP, FODSP_qoq, FODSP_yoy, DSPIC96_mom, DSPIC96_yoy, PCE_mom, PCE_yoy, PCEDG_mom, 
# PCEDG_yoy, PSAVERT, PSAVERT_mom, PSAVERT_yoy, DSPI_mom, DSPI_yoy, RSXFS_mom, RSXFS_yoy, 
# INDPRO, INDPRO_mom, INDPRO_yoy, TCU, TCU_mom, TCU_yoy, HOUST_mom, HOUST_yoy, 
# GPDI_qoq, GPDI_yoy, div_ratio, CP_qoq, CP_yoy, GFDEBTN_qoq, GFDEBTN_yoy, GFDEGDQ188S, 
# GFDEGDQ188S_qoq, GFDEGDQ188S_yoy, DIVIDEND_qoq, DIVIDEND_yoy, SPCS20RSA, SPCS20RSA_mom, SPCS20RSA_yoy, MULTPL_SHILLER_PE_RATIO_MONTH, 
# MULTPL_SHILLER_PE_RATIO_MONTH_mom, MULTPL_SHILLER_PE_RATIO_MONTH_yoy, 

# Future growth indicators are mostly correlated with each other
future_ind = []
for ind in macro_df.keys():
  if 'future' in ind:
    future_ind.append(ind)
  
print(future_ind)
# OUTPUT:
# ['SPX_future_growth_1d', 'SPX_future_growth_3d', 'SPX_future_growth_7d', 'SPX_future_growth_30d', 'SPX_future_growth_90d', 'SPX_future_growth_365d', 'DJI_future_growth_1d', 'DJI_future_growth_3d', 'DJI_future_growth_7d', 'DJI_future_growth_30d', 'DJI_future_growth_90d', 'DJI_future_growth_365d']


# include all features 
macro_df_no_future_ind = macro_df.keys()
# do not use future_ind in the list to find correlations with the label (which is a future_indicator)
macro_df_no_future_ind = macro_df_no_future_ind.drop(future_ind)

# imports
from collections import OrderedDict
from sklearn.tree import DecisionTreeRegressor
from matplotlib import pyplot

# all features should be numeric
for key in macro_df.keys():
  macro_df[key] = macro_df[key].astype(float)

# include all features 
X_keys = macro_df.keys()
# do not use future ind to predict
X_keys = X_keys.drop(future_ind)

# deep copy of the dataframe not to change the original df
macro_copy = macro_df.copy(deep=True)

macro_copy.fillna(0,inplace=True)
# macro_copy.dropna(inplace=True)

#get all features in X and dependent variable in y
X = macro_copy[X_keys]
y = macro_copy['SPX_future_growth_90d']

# define a function that returns an ordered dictionary of features, sorted by importance
def get_importance_features(model):
  importance = model.feature_importances_
  feat_imp = OrderedDict()
  # summarize feature importance
  for i,v in enumerate(importance):
    feat_imp[X.keys()[i]] = importance[i]

  # https://stackoverflow.com/questions/613183/how-do-i-sort-a-dictionary-by-value  
  sorted_feat_imp = sorted(feat_imp.items(), key=lambda kv: kv[1])

  return sorted_feat_imp

# init the class and fit the model
decision_tree_model = DecisionTreeRegressor()
decision_tree_model.fit(X, y)

decision_feat_imp = get_importance_features(decision_tree_model)