Export compiler.toml

analyses/constitutional_amendments.py

@@ -0,0 +1,70 @@
+import gptc
+
+amendments = [
+    ("1st", "First"),
+    ("2nd", "Second"),
+    ("3rd", "Third"),
+    ("4th", "Fourth"),
+    ("5th", "Fifth"),
+    ("6th", "Sixth"),
+    ("7th", "Seventh"),
+    ("8th", "Eighth"),
+    ("9th", "Ninth"),
+    ("10th", "Tenth"),
+    ("11th", "Eleventh"),
+    ("12th", "Twelfth"),
+    ("13th", "Thirteenth"),
+    ("14th", "Fourteenth"),
+    ("15th", "Fifteenth"),
+    ("16th", "Sixteenth"),
+    ("17th", "Seventeenth"),
+    ("18th", "Eighteenth"),
+    ("19th", "Nineteenth"),
+    ("20th", "Twentieth"),
+    ("21st", "Twenty-first"),
+    ("22nd", "Twenty-second"),
+    ("23rd", "Twenty-third"),
+    ("24th", "Twenty-fourth"),
+    ("25th", "Twenty-fifth"),
+    ("26th", "Twenty-sixth"),
+    ("27th", "Twenty-seventh"),
+]
+
+with open("model.gptc", "rb") as f:
+    model = gptc.deserialize(f)
+
+data = {}
+
+for number, name in amendments:
+    number_data = model.get(number + " Amendment")
+    name_data = model.get(name + " Amendment")
+
+    if number_data and not name_data:
+        data[name] = number_data
+    elif name_data and not number_data:
+        data[name] = name_data
+    elif number_data and name_data:
+        data[name] = {
+            key: (number_data[key] + name_data[key]) / 2
+            for key in number_data.keys()
+        }
+
+classified_amendments = sorted(data.items(), key=lambda x: x[1]["left"])
+
+print("# Constitutional Amendment Analysis")
+print()
+print("""This is an analysis of which amendments to the U.S. Constitution are mentioned
+more in right- or left-leaning American news sources. Data do not necessarily
+correlate with support or opposition for the amendment among right- or
+left-leaning Americans.""")
+print()
+print("| Amendment      | Left  | Right |")
+print("+----------------+-------+-------+")
+for amendment, data in classified_amendments:
+    percent_right = f"{data['right']*100:>4.1f}%"
+    percent_left = f"{data['left']*100:>4.1f}%"
+
+    amendment_padding = " "*(14 - len(amendment))
+    print(f"| {amendment}{amendment_padding} | {percent_left} | {percent_right} |")
+print("+----------------+-------+-------+")
+print("| Amendment      | Left  | Right |")

analyses/states.py

@@ -0,0 +1,85 @@
+import gptc
+
+states = [
+    "Alabama",
+    "Alaska",
+    "Arizona",
+    "Arkansas",
+    "California",
+    "Colorado",
+    "Connecticut",
+    "Delaware",
+    "Florida",
+    "Georgia",
+    "Hawaii",
+    "Idaho",
+    "Illinois",
+    "Indiana",
+    "Iowa",
+    "Kansas",
+    "Kentucky",
+    "Louisiana",
+    "Maine",
+    "Maryland",
+    "Massachusetts",
+    "Michigan",
+    "Minnesota",
+    "Mississippi",
+    "Missouri",
+    "Montana",
+    "Nebraska",
+    "Nevada",
+    "New Hampshire",
+    "New Jersey",
+    "New Mexico",
+    "New York",
+    "North Carolina",
+    "North Dakota",
+    "Ohio",
+    "Oklahoma",
+    "Oregon",
+    "Pennsylvania",
+    "Rhode Island",
+    "South Carolina",
+    "South Dakota",
+    "Tennessee",
+    "Texas",
+    "Utah",
+    "Vermont",
+    "Virginia",
+    "Washington",
+    "West Virginia",
+    "Wisconsin",
+    "Wyoming",
+]
+
+with open("model.gptc", "rb") as f:
+    model = gptc.deserialize(f)
+
+classified_states = []
+
+for state in states:
+    classified_states.append((state, model.get(state),))
+
+classified_states.sort(key=lambda x: x[1]["left"])
+
+longest = max([len(state) for state in states])
+
+print("# State Analysis")
+print()
+print("""This is an analysis of which states are mentioned more in right- or left-
+leaning American news sources. Results do not necessarily correlate with the
+political views of residents of the states; for example, the predominantly
+liberal state of Oregon is mentioned more in right-leaning sources than in
+left-leaning ones.""")
+print()
+print("| State          | Left  | Right |")
+print("+----------------+-------+-------+")
+for state, data in classified_states:
+    percent_right = f"{round(data['right']*1000)/10}%"
+    percent_left = f"{round(data['left']*1000)/10}%"
+
+    state_padding = " "*(longest - len(state))
+    print(f"| {state}{state_padding} | {percent_left} | {percent_right} |")
+print("+----------------+-------+-------+")
+print("| State          | Left  | Right |")

compile.py

@@ -32,13 +32,11 @@ raw_model = [
 ]
 
 with open("model.gptc", "w+b") as f:
-    f.write(
     gptc.compile(
         raw_model,
         max_ngram_length=config["max_ngram_length"],
         min_count=config["min_count"],
-        ).serialize()
+    ).serialize(f)
-    )
 
 con.commit()
 con.close()

compiler.toml

@@ -1,2 +1,2 @@
-max_ngram_length=8
+max_ngram_length=5
 min_count=5

export.py

@@ -28,6 +28,7 @@ os.mkdir("build")
 
 shutil.copy("articles.db", "build/articles.db")
 shutil.copy("sources.toml", "build/sources.toml")
+shutil.copy("compiler.toml", "build/compiler.toml")
 shutil.copy("model.gptc", "build/model.gptc")
 
 con = sqlite3.Connection("build/articles.db")