From 0040cc1545e58f55e7e48924d689771de43cb846 Mon Sep 17 00:00:00 2001
From: jackkolm <jack.kolm@outlook.com>
Date: Fri, 21 Mar 2025 01:55:36 +0100
Subject: [PATCH] accidentally removed dummy regressor code, readded
(project.py)
---
project/project.py | 176 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 176 insertions(+)
create mode 100644 project/project.py
diff --git a/project/project.py b/project/project.py
new file mode 100644
index 0000000..57e640a
--- /dev/null
+++ b/project/project.py
@@ -0,0 +1,176 @@
+import pandas as pd
+
+
+import matplotlib.pyplot as plt
+import numpy as np
+
+# This was needed for sklearn not to crash when importing the dummy for some reason
+def dummy_npwarn_decorator_factory():
+ def npwarn_decorator(x):
+ return x
+ return npwarn_decorator
+np._no_nep50_warning = getattr(np, '_no_nep50_warning', dummy_npwarn_decorator_factory)
+
+
+from sklearn.dummy import DummyClassifier, DummyRegressor
+from sklearn.naive_bayes import MultinomialNB, GaussianNB, BernoulliNB, CategoricalNB
+from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
+from sklearn.pipeline import Pipeline, FeatureUnion
+from sklearn.metrics import classification_report, precision_score, r2_score, mean_absolute_error, mean_squared_error
+from sklearn.feature_extraction.text import TfidfVectorizer
+
+def plot_games_on_meta_score(df):
+ scores = np.array(df["meta_score"])
+ scores_big = scores[scores > 75]
+ print(scores_big)
+ scores_small = scores[scores <= 75]
+ two_sets = [scores_big, scores_small]
+ plt.hist(two_sets, bins=10, stacked=True)
+ plt.xlabel("Meta Score")
+ plt.ylabel("Number of Games")
+ plt.show()
+
+
+def split_data(df):
+ """
+ Split data into two parts; a training dataset, and a test dataset.
+ Returns the two parts as a tuple.c
+ """
+ test_data = pd.DataFrame()
+ drop_indexes = []
+ for i in range(1, 101):
+ row = df.loc[df['meta_score'] == i]
+ if row.empty:
+ continue
+ if row.isnull().values.any():
+ print("null")
+ drop_indexes.append(row.index[0])
+
+ test_data = pd.concat([test_data, row])
+ data.drop(drop_indexes, inplace=True)
+
+ data = data.sample(frac=1.0, random_state=200)
+ training_data = data
+ return training_data, test_data
+
+def make_classes(df):
+
+ for index, row in df.iterrows():
+
+ if row["meta_score"] < 70:
+ df.at[index, "class"] = "bad"
+ elif row["meta_score"] < 80:
+ df.at[index, "class"] = "average"
+ else:
+ df.at[index, "class"] = "good"
+
+ bad_data = df.loc[df['class'] == "bad"]
+ good_data = df.loc[df['class'] == "good"]
+ average_data = df.loc[df['class'] == "average"]
+ least_amount = min([len(bad_data), len(good_data), len(average_data)])
+
+ bad_data = bad_data.sample(frac=1.0, random_state=200)
+ good_data = good_data.sample(frac=1.0, random_state=200)
+ average_data = average_data.sample(frac=1.0, random_state=200)
+ bad_data = bad_data[:least_amount]
+ good_data = good_data[:least_amount]
+ average_data = average_data[:least_amount]
+ classified_data = pd.concat([bad_data, good_data, average_data])
+ randomised_avg_data = classified_data.sample(frac=1.0, random_state=201)
+ classified_data = randomised_avg_data.dropna(subset=["summary"])
+
+ return classified_data
+
+
+
+def make_binary_classes(data):
+
+ for index, row in df.iterrows():
+
+ if row["meta_score"] < 75:
+ data.at[index, "class"] = "bad"
+ else:
+ data.at[index, "class"] = "good"
+ bad_data = df.loc[df['class'] == "bad"]
+ good_data = df.loc[df['class'] == "good"]
+ least_amount = min([len(bad_data), len(good_data)])
+
+ bad_data = bad_data.sample(frac=1.0, random_state=200)
+ good_data = good_data.sample(frac=1.0, random_state=200)
+ bad_data = bad_data[:least_amount]
+ good_data = good_data[:least_amount]
+ data = pd.concat([bad_data, good_data])
+ randomised_data = data.sample(frac=1.0, random_state=201)
+ data = randomised_data
+ data = data.dropna(subset=["summary"])
+
+ return data
+
+
+
+def plot_classified_data(data):
+ """
+ Plot the data returned from and classified in make_classes().
+ Amount for each of the three classes (good, bad, average) is displayed, ONLY.
+ Three bins, one for the amount of good, one for averge, and one for bad.
+ """
+ good = data['class'].value_counts()["good"]
+ average = data['class'].value_counts()["average"]
+ bad = data['class'].value_counts()["bad"]
+ #print(good, average, bad)
+ data = [good, average, bad]
+ plt.bar(["Good", "Average", "Bad"], data)
+ plt.xlabel("Class")
+ plt.ylabel("Number of Games")
+ plt.show()
+
+
+
+
+
+def dummy_regressor(train_X, train_Y, test_X, test_Y):
+ dummy_regr = DummyRegressor(strategy="mean")
+
+ dummy_regr.fit(train_X, train_Y)
+
+ pred = dummy_regr.predict(test_X)
+ scr = dummy_regr.score(test_X, test_Y)
+
+ r2 = r2_score(test_Y, pred)
+ mar = mean_absolute_error(test_Y, pred)
+ msq = mean_squared_error(test_Y, pred)
+
+ print(f"MSE: {msq}, MAE: {mar}, R2: {r2}")
+ #print(msq)
+ #print(pred)
+ #print(test_Y)
+ #print(r2)
+ #classification_report(test_Y, pred)
+ #dummy_regr.score(X, y)
+ #model = multinomial_naive_bayes_classifier_model(train_X, train_Y)
+ dc_stratified = DummyClassifier(strategy='stratified')
+ dc_model = dc_stratified.fit(train_X, train_Y)
+ #print(model.score(test_X, test_Y))
+ dc_predicted = dc_model.predict(test_X)
+ #print(classification_report(test_Y, dc_predicted))
+
+def predict_against_test_data(test_data, model):
+ test_X = np.array(test_data["summary"])
+ test_Y = np.array(test_data["class"])
+ predicted = model.predict(test_X)
+ score = (precision_score(test_Y, predicted, average='macro'))
+ print(f'Macro precision score against test data: {score}')
+ print("Classification report against test data:")
+ print(classification_report(test_Y, predicted))
+if __name__ == "__main__":
+
+ file_path = 'C:\\repos\\text-mining\\project\\all_games.csv'
+
+ df = pd.read_csv(file_path)
+
+ print(df.head())
+ plot_games_on_meta_score(df)
+ from load_data import prep_data
+ train_X, train_Y, test_X, test_Y = prep_data(df)
+ dummy_regressor(train_X, train_Y, test_X, test_Y)
+
--
GitLab