تدريب نموذج شجرة القرار - كتاب الذكاء الإصطناعي - الصف 12 - الفصل 1 - المملكة العربية السعودية

لديك الآن 1,400 نقطة بيانات ستُستخدم لتدريب النموذج و 600 نقطة ستُستخدم لاختباره. ابدأ بتدريب نموذج شجرة القرار وتمثيله:from sklearn.tree import plot_tree import matplotlib.pyplot as plt my_tree=diagnose_v4(train_data) # train a model print(my_tree.classes_) # print the possible target labels (diagnoses)plt.figure(figsize=(12,6)) # size of the visualization, in inches# plot the tree plot_tree(my_tree, max_depth=2, fontsize=10, feature_names=medical_dataset.columns[:-1] )['allergies' 'common cold' 'covid19' 'flu']شكل 2.13: نموذج شجرة القرار لمجموعة بيانات medical_data (البيانات الطبية) بعمق مستويين2023 - 1447--- VISUAL CONTEXT --- **DIAGRAM**: نموذج شجرة القرار لمجموعة بيانات medical_data (البيانات الطبية) بعمق مستويين Description: A decision tree diagram illustrating a classification model for medical diagnoses. The tree has a root node and branches down to a maximum depth of 2, as specified in the Python code. Each node represents a decision based on a symptom threshold (e.g., 'fever <= 0.5'). Inside each node, the 'gini' impurity, the number of 'samples', and the 'value' (a list representing the distribution of the four target classes: allergies, common cold, covid19, flu) are displayed. The leaf nodes are indicated by '[...]'. Data: The decision tree starts with a root node: 'fever <= 0.5', gini = 0.75, samples = 1400, value = [354, 345, 358, 343].If 'fever <= 0.5' is true (left branch), it leads to a node: 'sore throat <= 0.5', gini = 0.606, samples = 791, value = [354, 340, 71, 26]. From this node, if 'sore throat <= 0.5' is true (left branch), it leads to a node: 'runny nose <= 0.5', gini = 0.497, samples = 526, value = [354, 101, 58, 13]. This is a leaf node, indicated by '[...]'. If 'sore throat <= 0.5' is false (right branch), it leads to a node: 'tiredness <= 0.5', gini = 0.182, samples = 265, value = [0, 239, 13, 13]. This is a leaf node, indicated by '[...]'.If 'fever <= 0.5' is false (right branch), it leads to a node: 'sore throat <= 0.5', gini = 0.507, samples = 609, value = [0, 5, 287, 317]. From this node, if 'sore throat <= 0.5' is true (left branch), it leads to a node: 'sneezing <= 0.5', gini = 0.387, samples = 317, value = [0, 2, 235, 80]. This is a leaf node, indicated by '[...]'. If 'sore throat <= 0.5' is false (right branch), it leads to a node: 'headache <= 0.5', gini = 0.309, samples = 292, value = [0, 3, 52, 237]. This is a leaf node, indicated by '[...]'. Key Values: Decision criteria (e.g., symptom <= threshold), Gini impurity values (e.g., 0.75, 0.606), Number of samples (e.g., 1400, 791), Class distribution arrays (value = [count_allergies, count_common_cold, count_covid19, count_flu]), Target labels: allergies, common cold, covid19, flu Context: This diagram visually represents the decision-making process of a machine learning model (decision tree) trained on medical data. It shows how different symptoms (features) are used to split the data and classify patients into different diagnoses (target labels) based on the Gini impurity metric, aiming to reduce impurity at each split. The 'max_depth=2' parameter limits the tree's complexity, resulting in a tree with a root node and two levels of splits.