diff --git a/python1/predict.py b/python1/predict.py
new file mode 100644
index 0000000000000000000000000000000000000000..90763695c3c5ff4bac658fe1f29911b2e3166846
--- /dev/null
+++ b/python1/predict.py
@@ -0,0 +1,48 @@
+import numpy as np
+
+
+datas = [
+    {"city": "吕梁", "area": 80, "rooms": 2, "school": 1, "style": 0, "price": 5000},
+    {"city": "太原", "area": 100, "rooms": 3, "school": 0, "style": 1, "price": 7000},
+    {"city": "吕梁", "area": 120, "rooms": 4, "school": 1, "style": 1, "price": 9000},
+    {"city": "太原", "area": 90, "rooms": 2, "school": 0, "style": 0, "price": 6000},
+    {"city": "吕梁", "area": 75, "rooms": 3, "school": 1, "style": 0, "price": 5500},
+    {"city": "太原", "area": 110, "rooms": 3, "school": 1, "style": 1, "price": 8000},
+    {"city": "吕梁", "area": 95, "rooms": 2, "school": 0, "style": 1, "price": 6500},
+    {"city": "太原", "area": 85, "rooms": 4, "school": 0, "style": 0, "price": 7500},
+    {"city": "吕梁", "area": 65, "rooms": 1, "school": 1, "style": 0, "price": 4500},
+    {"city": "太原", "area": 105, "rooms": 3, "school": 1, "style": 1, "price": 8500},
+    {"city": "晋中", "area": 130, "rooms": 4, "school": 1, "style": 1, "price": 9500},
+    {"city": "晋中", "area": 75, "rooms": 2, "school": 0, "style": 0, "price": 5500},
+    {"city": "晋中", "area": 95, "rooms": 3, "school": 1, "style": 0, "price": 6500},
+    {"city": "晋中", "area": 110, "rooms": 4, "school": 0, "style": 1, "price": 8000},
+    {"city": "晋中", "area": 85, "rooms": 2, "school": 1, "style": 1, "price": 7000}
+]
+
+X = []  # 特征值
+Y = []  # 标签值
+city_mark = {"吕梁": 1, "太原": 2, "晋中": 3}  # 城市标记
+
+for item in datas:
+    single = []
+    single.append(city_mark[item["city"]])
+    single.append(item["area"])
+    single.append(item["rooms"])
+    single.append(item["school"])
+    single.append(item["style"])
+    X.append(single)
+    Y.append(item["price"])
+
+X = np.array(X)
+Y = np.array(Y)
+
+# 添加偏置项
+X = np.hstack((np.ones((X.shape[0], 1)), X))
+
+# 计算theta
+theta = np.linalg.pinv(X.T.dot(X)).dot(X.T).dot(Y)
+
+# 预测示例
+input_features = np.array([3, 2, 150, 2, 1, 1])  # 假设第一个元素是偏置项
+prediction = theta.dot(input_features)
+print(prediction)