|
|
@@ -1,11 +1,10 @@
|
|
|
import pandas as pd
|
|
|
import joblib
|
|
|
from sklearn.ensemble import RandomForestRegressor
|
|
|
-from sklearn.model_selection import train_test_split
|
|
|
|
|
|
# === 配置路径 ===
|
|
|
-csv_path = 'C:\\Users\\Administrator\\Desktop\\defrost\\feedback_data.csv'
|
|
|
-model_save_path = "defrost_time_corrector.pkl"
|
|
|
+csv_path = 'C:\\Users\\Administrator\\Desktop\\defrost\\feedback_data.csv' # 你的csv
|
|
|
+model_save_path = "defrost_time_corrector.pkl" # 模型保存路径
|
|
|
|
|
|
# === 特征列定义 ===
|
|
|
feature_columns = [
|
|
|
@@ -14,21 +13,43 @@ feature_columns = [
|
|
|
]
|
|
|
|
|
|
# === 1. 读取CSV并预处理 ===
|
|
|
-df = pd.read_csv(csv_path, parse_dates=["t_formula", "t_real"], encoding='gbk')
|
|
|
-
|
|
|
-# 确保字段类型正确
|
|
|
-df["material_name"] = df["material_name"].astype(str)
|
|
|
-df["manufactured_goods"] = df["manufactured_goods"].astype(str)
|
|
|
+try:
|
|
|
+ df = pd.read_csv(csv_path, parse_dates=["t_formula", "t_real"], encoding='gbk')
|
|
|
+ print(f"✅ 成功读取CSV文件，共{len(df)}条数据")
|
|
|
+except Exception as e:
|
|
|
+ print(f"❌ 读取CSV失败: {e}")
|
|
|
+ exit(1)
|
|
|
+
|
|
|
+# 确保字段类型正确（如果这两列存在）
|
|
|
+for col in ["material_name", "manufactured_goods"]:
|
|
|
+ if col in df.columns:
|
|
|
+ df[col] = df[col].astype(str)
|
|
|
|
|
|
# 计算真实解冻时长（小时）
|
|
|
df["t_real_hours"] = (df["t_real"] - df["t_formula"]).dt.total_seconds() / 3600
|
|
|
|
|
|
-# === 2. 训练模型（用已有所有历史数据） ===
|
|
|
+# 检查有没有缺失特征
|
|
|
+missing_features = [col for col in feature_columns if col not in df.columns]
|
|
|
+if missing_features:
|
|
|
+ print(f"❌ 缺少必要特征列: {missing_features}")
|
|
|
+ exit(1)
|
|
|
+
|
|
|
+# === 2. 智能训练模型 ===
|
|
|
X = df[feature_columns]
|
|
|
y = df["t_real_hours"]
|
|
|
|
|
|
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
|
|
|
-
|
|
|
+if len(X) >= 10:
|
|
|
+ # 数据够多，做train_test_split
|
|
|
+ from sklearn.model_selection import train_test_split
|
|
|
+ X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
|
|
|
+ print(f"📚 数据量 {len(X)}，已划分训练集和测试集")
|
|
|
+else:
|
|
|
+ # 数据少，直接全量训练
|
|
|
+ X_train, y_train = X, y
|
|
|
+ X_test, y_test = None, None
|
|
|
+ print(f"⚠️ 数据量太少（{len(X)}条），直接全量训练")
|
|
|
+
|
|
|
+# 建立随机森林回归模型
|
|
|
model = RandomForestRegressor(n_estimators=100, random_state=42)
|
|
|
model.fit(X_train, y_train)
|
|
|
|
|
|
@@ -36,10 +57,8 @@ model.fit(X_train, y_train)
|
|
|
joblib.dump(model, model_save_path)
|
|
|
print(f"✅ 模型训练完成，已保存为 {model_save_path}")
|
|
|
|
|
|
-# === 3. 用最新数据预测（比如最后一条或多条） ===
|
|
|
-
|
|
|
-# 假设你要预测最后新增的一条数据（如果多条可以改）
|
|
|
-new_sample = df.tail(1) # 取最后一行，也可以是 tail(n) 最后n行
|
|
|
+# === 3. 预测最新一条数据 ===
|
|
|
+new_sample = df.tail(1) # 取最后一行
|
|
|
|
|
|
X_new = new_sample[feature_columns]
|
|
|
predicted_time = model.predict(X_new)[0]
|
|
|
@@ -48,8 +67,11 @@ predicted_time = model.predict(X_new)[0]
|
|
|
df.loc[new_sample.index, "predicted_t_real_hours"] = predicted_time
|
|
|
|
|
|
# === 4. 保存带预测值的CSV ===
|
|
|
-df.to_csv(csv_path, encoding='gbk', index=False)
|
|
|
-print(f"✅ 最新数据预测完成，已更新到 {csv_path}")
|
|
|
+try:
|
|
|
+ df.to_csv(csv_path, encoding='gbk', index=False)
|
|
|
+ print(f"✅ 最新数据预测完成，已更新到 {csv_path}")
|
|
|
+except Exception as e:
|
|
|
+ print(f"❌ 保存CSV失败: {e}")
|
|
|
|
|
|
+# === 5. 打印最终预测结果 ===
|
|
|
print(f"\n📊 预测最后一条数据真实解冻时间为：{predicted_time:.2f} 小时")
|
|
|
-
|
Administrator