Adding code to create speeches CSV dataset from json files, the created CSV file itself, plus EDA notebook

.gitignore

@@ -1,3 +1,6 @@
+# Folder of json files containing speech data
+data/speeches/
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[codz]

scripts/create_dataframe.py

@@ -0,0 +1,30 @@
+import os
+from pathlib import Path
+import pandas as pd
+
+def build_df_from_json_files(json_folder, output_file):
+    """
+    Combines all JSON files in `json_folder` into one DataFrame.
+    If `output_file` already exists, loads it instead of rebuilding.
+    """
+    # check if file already exists
+    if os.path.exists(output_file):
+        print(f"File already exists")
+        return
+    else:
+        # if file doesn't exist, combine files within `json_folder` into a dataframe
+        print("Building new combined DataFrame from JSON files")
+        paths = Path(json_folder).glob("*.json")
+        df = pd.DataFrame([pd.read_json(p, typ="series") for p in paths])
+        print(f"Combined DataFrame saved to {output_file}")
+        # save to path specified by `output_file` 
+        df.to_csv(output_file)
+
+    return 
+
+# preparing for execution in terminal
+if __name__ == "__main__":
+    json_folder = "../data/speeches" # source of json files 
+    output_file = "../data/all_speeches.csv" # path for combined dataframe
+
+    df = build_df_from_json_files(json_folder, output_file)

src/mypkg/mymodule.py

@@ -1,3 +1,3 @@
 def test():
-    print("Hello world! I speak Python!")
+    print("Hello world! I speak English and Python!")