معالجة البيانات وتحليل المشاعر - كتاب الذكاء الإصطناعي - الصف 12 - الفصل 1 - المملكة العربية السعودية

# load the train and testing data. imdb_train_reviews=pd.read_csv('imdb_data/imdb_train.csv') imdb_test_reviews=pd.read_csv('imdb_data/imdb_test.csv') imdb_train_reviews وكما يتضح في الشكل 3.3، فإن مجموعة بيانات DataFrame تحتوي على عمودين: • نص التقييم. • القيم (الصنف). القيمة 0 تمثل تقييمًا سلبيًا بينما القيمة 1 تمثل تقييمًا إيجابيًا. الخطوة التالية هي إسناد أعمدة النص والقيم إلى متغيرات مستقلة في أمثلة التدريب والاختبار الممثلة كمجموعة بيانات DataFrame كما يلي: يُستخدم الرمزان X و Y عادة في التعلم الموجه فيعبر X عن البيانات المدخلة للتنبؤ، و Y عن القيم المستهدفة. # extract the text from the 'text' column for both training and testing. X_train_text=imdb_train_reviews['text'] X_test_text=imdb_test_reviews['text'] # extract the labels from the 'label' column for both training and testing. Y_train=imdb_train_reviews['label'] Y_test=imdb_test_reviews['label'] X_train_text # training data in text format شكل 3.3: مجموعة بيانات التدريب المعنونة شكل 3.4: صورة من أمثلة التدريب (X_train_text) من مجموعة بيانات DataFrame وزارة التعليم Ministry of Education 2023 - 1447 136 --- VISUAL CONTEXT --- **TABLE**: شكل 3.3: مجموعة بيانات التدريب المعنونة Description: A Pandas DataFrame displaying movie review text and corresponding sentiment labels. It shows the first 5 and last 5 rows of a dataset with 40,000 entries. Table Structure: Headers: text | label Rows: Row 1: I grew up (b. 1965) watching and loving the Th... | 0 Row 2: When I put this movie in my DVD player, and sa... | 0 Row 3: Why do people who do not know what a particula... | 0 Row 4: Even though I have great interest in Biblical ... | 0 Row 5: Im a die hard Dads Army fan and nothing will e... | 1 Row 6: ... | ... Row 7: "Western Union" is something of a forgotten cl... | 1 Row 8: This movie is an incredible piece of work. It ... | 1 Row 9: My wife and I watched this movie because we pl... | 0 Row 10: When I first watched Flatliners, I was amazed.... | 1 Row 11: Why would this film be so good, but only gross... | 1 Data: The DataFrame has two columns: 'text' containing movie review strings and 'label' containing binary sentiment indicators (0 or 1). Key Values: 40000 rows × 2 columns Context: This DataFrame serves as an example of a labeled dataset used in machine learning for tasks like sentiment analysis, where text input is associated with a target output (sentiment label). **DIAGRAM**: Untitled Description: A flow diagram illustrating the mapping of numerical labels to sentiment categories. An arrow connects 'label: 1' from the DataFrame to a blue oval labeled 'تقييم إيجابي' (Positive review). Another arrow connects 'label: 0' to a blue oval labeled 'تقييم سلبي' (Negative review). Key Values: تقييم إيجابي, تقييم سلبي Context: This diagram clarifies the meaning of the binary labels (0 and 1) used in the dataset, which represent negative and positive sentiment respectively, crucial for understanding the sentiment analysis task. **TABLE**: شكل 3.4: صورة من أمثلة التدريب (X_train_text) من مجموعة بيانات DataFrame Description: A Pandas Series representing the 'text' column extracted from the imdb_train_reviews DataFrame. It shows the index and the review text, along with metadata about the Series. Table Structure: Headers: N/A Rows: Row 1: 0 I grew up (b. 1965) watching and loving the Th... Row 2: 1 When I put this movie in my DVD player, and sa... Row 3: 2 Why do people who do not know what a particula... Row 4: 3 Even though I have great interest in Biblical ... Row 5: 4 Im a die hard Dads Army fan and nothing will e... Row 6: ... Row 7: 39995 "Western Union" is something of a forgotten cl... Row 8: 39996 This movie is an incredible piece of work. It ... Row 9: 39997 My wife and I watched this movie because we pl... Row 10: 39998 When I first watched Flatliners, I was amazed.... Row 11: 39999 Why would this film be so good, but only gross... Data: The Series contains 40,000 entries of type 'object' (strings), representing the movie review texts. Key Values: Name: text, Length: 40000, dtype: object Context: This visual demonstrates the extraction of a specific feature (the text content) from the main dataset to be used as the independent variable (X) in a supervised machine learning model.