update reproduce.sh

binder/environment.yml

@@ -4,6 +4,7 @@ channels:
 dependencies:
   - python=3.9
   - ipywidgets
+  - jupyter
   - jupyterlab
   - matplotlib
   - numpy
@@ -13,8 +14,8 @@ dependencies:
   - lxml
   - requests
   - statsmodels
+  - pip
   - pip:
-    - pandas-datareader
-    - fredpy
-    - statsmodels
-
+      - pandas-datareader
+      - fredpy
+      - statsmodels

code/main/parse_GB_raw_data.py

@@ -1,5 +1,4 @@
 import pandas as pd
-import os
 
 # Load the Excel file
 excel_file = pd.ExcelFile('data/raw/GBweb_Row_Format.xlsx') 
@@ -81,10 +80,6 @@
     for column in GB_df.columns[1:]:
         GB_df[column] = GB_df[column].apply(lambda x: f"{x:.{decimal}f}")
 
-current_directory = os.path.dirname(os.path.abspath(__file__))
-file_path = "/../data/output/FRED.csv"
-GB_df.to_csv(current_directory + file_path)
-
 # Uncomment these final lines to get the output of your choice
-#GB_df.to_csv('data/output/GB.csv')
+GB_df.to_csv('data/output/GB.csv')
 # GB_df.to_excel('data/output/GB_parsed.xlsx', index=False)

code/main/parse_SPF_raw_data.py

@@ -1,5 +1,4 @@
 import pandas as pd
-import os
 
 # Load the Excel file with levels first
 excel_file = pd.ExcelFile('data/raw/meanLevel.xlsx') 
@@ -69,10 +68,6 @@
     for column in results_df.columns[1:]:
         results_df[column] = results_df[column].apply(lambda x: f"{x:.{decimal}f}")
 
-current_directory = os.path.dirname(os.path.abspath(__file__))
-file_path = "/../data/output/FRED.csv"
-results_df.to_csv(current_directory + file_path)
-
 # Uncomment these final lines to get the output of your choice
-# results_df.to_csv('data/output/SPF.csv')
+results_df.to_csv('data/output/SPF.csv')
 # SPF_df.to_excel('data/output/SPF_parsed.xlsx', index=False)

code/main/reproduce.py

@@ -8,12 +8,12 @@
 
 # List all files in the current directory
 files_to_run = [
-    "/parse_GB_raw_data.py",
-    "/parse_SPF_raw_data.py",
-    "/scrape_FRED_data.py",
-    "/annual_forecasts.py",
-    "/compute_abs_error.py",
-    "/abse_reg.py"
+    "./code/main/parse_GB_raw_data.py",
+    "./code/main/parse_SPF_raw_data.py",
+    "./code/main/scrape_FRED_data.py",
+    "./code/main/annual_forecasts.py",
+    "./code/main/compute_abs_error.py",
+    "./code/main/abse_reg.py"
 ]
 
 # Measure the start time
@@ -22,7 +22,7 @@
 # Run each Python script in the directory
 for python_file in files_to_run:
     if python_file != "reproduce.py":  # Exclude the launcher script itself
-        subprocess.run(["python", current_directory + python_file])
+        subprocess.run(["python", python_file])
 
 end_time = time.time()
 

code/main/scrape_FRED_data.py

@@ -2,7 +2,6 @@
 import numpy as np
 import fredpy as fp
 import matplotlib.pyplot as plt
-import os
 
 fp.api_key = "c735c085b4e162a17326871bc1d5c625"
 win = ['01-01-1982','12-01-2017']
@@ -30,10 +29,6 @@
     for column in obs_df.columns[1:]:
         obs_df[column] = obs_df[column].apply(lambda x: f"{x:.{decimal}f}")
 
-current_directory = os.path.dirname(os.path.abspath(__file__))
-file_path = "/../data/output/FRED.csv"
-obs_df.to_csv(current_directory + file_path)
-
-#obs_df.to_csv('data/output/FRED.csv')
+obs_df.to_csv('data/output/FRED.csv')
 
 # obs_df.to_excel('data/output/FRED_scraped.xlsx', index=False)

reproduce.sh

@@ -5,7 +5,7 @@ SCPT_DIR=$(cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd)
 cd "$SCPT_DIR"
 
 mamba env update -f binder/environment.yml
-conda activate rs100_discussion
+source activate rs100_discussion
 
 ipython *.ipynb
 

results/abse_reg_1983.txt

@@ -5,7 +5,7 @@ Dep. Variable:         GB_error_unemp   R-squared:                       0.013
 Model:                            OLS   Adj. R-squared:                  0.006
 Method:                 Least Squares   F-statistic:                     1.760
 Date:                Wed, 21 Feb 2024   Prob (F-statistic):              0.187
-Time:                        08:35:09   Log-Likelihood:                -118.32
+Time:                        10:04:35   Log-Likelihood:                -118.32
 No. Observations:                 144   AIC:                             240.6
 Df Residuals:                     142   BIC:                             246.6
 Df Model:                           1                                         
@@ -25,15 +25,15 @@ Kurtosis:                      15.518   Cond. No.                         10.4
 Notes:
 [1] Standard Errors are heteroscedasticity robust (HC3)
 Mean Squared Error for GB_error_unemp: 0.3028
-Durbin-Watson Statistic for GB_error_unemp: 0.4990387828073439
+Durbin-Watson Statistic for GB_error_unemp: 0.4990387828073438
 Regression Summary for SPF_error_unemp:
                             OLS Regression Results                            
 ==============================================================================
 Dep. Variable:        SPF_error_unemp   R-squared:                       0.005
 Model:                            OLS   Adj. R-squared:                 -0.002
 Method:                 Least Squares   F-statistic:                    0.6700
 Date:                Wed, 21 Feb 2024   Prob (F-statistic):              0.414
-Time:                        08:35:09   Log-Likelihood:                -125.71
+Time:                        10:04:35   Log-Likelihood:                -125.71
 No. Observations:                 144   AIC:                             255.4
 Df Residuals:                     142   BIC:                             261.4
 Df Model:                           1                                         
@@ -53,15 +53,15 @@ Kurtosis:                      13.710   Cond. No.                         10.4
 Notes:
 [1] Standard Errors are heteroscedasticity robust (HC3)
 Mean Squared Error for SPF_error_unemp: 0.3356
-Durbin-Watson Statistic for SPF_error_unemp: 0.380336402078763
+Durbin-Watson Statistic for SPF_error_unemp: 0.3803364020787631
 Regression Summary for GB_error_cons:
                             OLS Regression Results                            
 ==============================================================================
 Dep. Variable:          GB_error_cons   R-squared:                       0.219
 Model:                            OLS   Adj. R-squared:                  0.214
 Method:                 Least Squares   F-statistic:                     30.02
 Date:                Wed, 21 Feb 2024   Prob (F-statistic):           1.89e-07
-Time:                        08:35:10   Log-Likelihood:                -166.53
+Time:                        10:04:35   Log-Likelihood:                -166.53
 No. Observations:                 144   AIC:                             337.1
 Df Residuals:                     142   BIC:                             343.0
 Df Model:                           1                                         
@@ -89,7 +89,7 @@ Dep. Variable:         SPF_error_cons   R-squared:                       0.133
 Model:                            OLS   Adj. R-squared:                  0.127
 Method:                 Least Squares   F-statistic:                     26.15
 Date:                Wed, 21 Feb 2024   Prob (F-statistic):           1.01e-06
-Time:                        08:35:10   Log-Likelihood:                -177.99
+Time:                        10:04:35   Log-Likelihood:                -177.99
 No. Observations:                 144   AIC:                             360.0
 Df Residuals:                     142   BIC:                             365.9
 Df Model:                           1