From bb4dfc9ffca39a127df193f2862dfed047e0201f Mon Sep 17 00:00:00 2001
From: "Mcintosh, Liam S (UG - Computer Science)" <lm00840@surrey.ac.uk>
Date: Mon, 24 May 2021 13:14:34 +0100
Subject: [PATCH] Update build.py
---
build.py | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/build.py b/build.py
index 0f57d9f..dc83f4b 100644
--- a/build.py
+++ b/build.py
@@ -18,6 +18,9 @@ from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from datetime import datetime
+import warnings
+warnings.filterwarnings('ignore')
+
#Functions for splitting into train/test sets.
def split_dataset(df, test_size=0.25):
movies_train, movies_test = train_test_split(df, test_size=test_size, shuffle=True)
@@ -44,6 +47,7 @@ vectorizer = CountVectorizer()
# url = "https://github.com/Jamchello/WikiMoviePlots/blob/master/wiki_movie_plots_deduped.csv?raw=true"
movies = pd.read_csv('./data/Data.csv', delimiter=",")
+print("Pre-processing data...")
MIN_MOVIES = 500
movies['Count'] = 1
@@ -446,13 +450,16 @@ upsampled_df = pd.concat(resampled)
movies = upsampled_df.copy()
optimal_val_split_lr = 0.1
+print("Training model...")
movies_train, movies_test, x_train_lr, y_train_lr, x_test_lr, y_test_lr = get_train_test(upsampled_df, test_size=optimal_val_split_lr)
lr_classifier = LogisticRegression(max_iter=2000)
classifier = OneVsRestClassifier(lr_classifier)
classifier.fit(x_train_lr, y_train_lr)
+print("Pickling files...")
for item in ['mlb', 'vectorizer','model']:
+ print("Saving " + f'{item}.pickle')
with open(f'{item}.pickle', 'wb') as handle:
pickle.dump(item, handle)
--
GitLab