国产区精品福利在线观看精品,亚洲精品国产电影午夜,精品国产免费观看久久久

df['Date'] = pd.to_datetime(df['Year'].astype(str) + '-' + df['Day'].astype(str), format='%Y-%j') df.set_index('Date', inplace=True) df.drop(['Year', 'Day'], axis=1, inplace=True) # 生成時間范圍 start_date = pd.Timestamp('1990-01-01') end_date = pd.Timestamp('2023-03-01') date_range = pd.date_range(start=start_date, end=end_date, freq='D') # 檢查時間范圍中是否包含DataFrame中的所有日期 missing_dates = date_range[~date_range.isin(df.index)] print("Missing Dates:")

代碼將DataFrame中的“Year”和“Day”列合并成日期，并設置為DataFrame的索引，然后生成一個時間范圍，檢查該范圍中是否包含了DataFrame中的所有日期，避免時間范圍不完整存在缺失。

# 定義劃分比例 train_ratio = 0.7 val_ratio = 0.1 test_ratio = 0.2 # 計算劃分的索引 train_split = int(train_ratio * len(df)) val_split = int((train_ratio + val_ratio) * len(df)) # 劃分數據集 train_set = df.iloc[:train_split] val_set = df.iloc[train_split:val_split] test_set = df.iloc[val_split:] plt.figure(figsize=(15, 10)) plt.subplot(3,1,1) plt.plot(train_set, color='g', alpha=0.3) plt.title('train Temperature時序圖') plt.subplot(3,1,2) plt.plot(val_set, color='b', alpha=0.3) plt.title('val Temperature時序圖') plt.subplot(3,1,3) plt.plot(test_set, color='r', alpha=0.3) plt.title('test Temperature時序圖') plt.xticks(rotation=45) plt.show()

數據集按照指定的比例劃分為訓練集、驗證集和測試集，并繪制它們的時序圖，訓練集用于訓練模型，驗證集用于調整模型超參數和評估性能，測試集用于評估模型在未知數據上的性能。

from sklearn.preprocessing import MinMaxScaler def normalize_dataframe(train_set, val_set, test_set): scaler = MinMaxScaler() scaler.fit(train_set) # 在訓練集上擬合歸一化模型 train = pd.DataFrame(scaler.transform(train_set), columns=train_set.columns, index = train_set.index) val = pd.DataFrame(scaler.transform(val_set), columns=val_set.columns, index = val_set.index) test = pd.DataFrame(scaler.transform(test_set), columns=test_set.columns, index = test_set.index) return train, val, test train, val, test = normalize_dataframe(train_set, val_set, test_set) plt.figure(figsize=(15, 10)) plt.subplot(3,1,1) plt.plot(train, color='g', alpha=0.3) plt.title('train Temperature歸一化時序圖') plt.subplot(3,1,2) plt.plot(val, color='b', alpha=0.3) plt.title('val Temperature歸一化時序圖') plt.subplot(3,1,3) plt.plot(test, color='r', alpha=0.3) plt.title('test Temperature歸一化時序圖') plt.xticks(rotation=45) plt.show()

將訓練集、驗證集和測試集進行歸一化，并繪制歸一化后的時序圖，這里歸一化采用訓練集統計指標避免出現數據泄露。

def prepare_data(data, win_size): X = [] y = [] for i in range(len(data) - win_size): temp_x = data[i:i + win_size] temp_y = data[i + win_size] X.append(temp_x) y.append(temp_y) X = np.asarray(X) y = np.asarray(y) X = np.expand_dims(X, axis=-1) return X, y win_size = 30 # 訓練集 X_train, y_train= prepare_data(train['Temperature'].values, win_size) # 驗證集 X_val, y_val= prepare_data(val['Temperature'].values, win_size) # 測試集 X_test, y_test = prepare_data(test['Temperature'].values, win_size) print("訓練集形狀:", X_train.shape, y_train.shape) print("驗證集形狀:", X_val.shape, y_val.shape) print("測試集形狀:", X_test.shape, y_test.shape)

2.3 BiLSTM模型構建

from tensorflow.keras.models import Sequential from tensorflow.keras.layers import LSTM, Bidirectional, Dense model_bilstm = Sequential() model_bilstm.add(Bidirectional(LSTM(128, activation='relu'), input_shape=(X_train.shape[1], X_train.shape[2]))) model_bilstm.add(Dense(64, activation='relu')) model_bilstm.add(Dense(32, activation='relu')) model_bilstm.add(Dense(16, activation='relu')) model_bilstm.add(Dense(1)) model_bilstm.compile(optimizer='adam', loss='mse') history = model_bilstm.fit(X_train, y_train, epochs=50, batch_size=32, validation_data=(X_val, y_val)) plt.figure() plt.plot(history.history['loss'], c='b', label = 'loss') plt.plot(history.history['val_loss'], c='g', label = 'val_loss') plt.legend() plt.show()

from sklearn import metrics y_pred = model_bilstm.predict(X_test) # 計算均方誤差（MSE） mse = metrics.mean_squared_error(y_test, np.array([i for arr in y_pred for i in arr])) # 計算均方根誤差（RMSE） rmse = np.sqrt(mse) # 計算平均絕對誤差（MAE） mae = metrics.mean_absolute_error(y_test, np.array([i for arr in y_pred for i in arr])) from sklearn.metrics import r2_score # 擬合優度 r2 = r2_score(y_test, np.array([i for arr in y_pred for i in arr])) print("均方誤差 (MSE):", mse) print("均方根誤差 (RMSE):", rmse) print("平均絕對誤差 (MAE):", mae) print("擬合優度:", r2)

# 取出預測的最后一個時間步的輸出作為下一步的輸入 last_output = model_bilstm.predict(X_test)[-1] # 預測的時間步數 steps = 10 # 假設向后預測10個時間步 predicted = [] for i in range(steps): # 將最后一個輸出加入X_test，繼續向后預測 input_data = np.append(X_test[-1][1:], last_output).reshape(1, X_test.shape[1], X_test.shape[2]) # 使用模型進行預測 next_output = model_bilstm.predict(input_data) # 將預測的值加入結果列表 predicted.append(next_output[0][0]) last_output = next_output[0] # 反歸一化 df_max = np.max(train_set) df_min = np.min(train_set) series_1 = np.array(predicted)*(df_max-df_min)+df_min plt.figure(figsize=(15,4), dpi =300) plt.subplot(3,1,1) plt.plot(train_set, color = 'c', label = '訓練集') plt.plot(val_set, color = 'r', label = '驗證集') plt.plot(test_set, color = 'b', label = '測試集') plt.plot(pd.date_range(start='2016-08-12', end='2023-03-01', freq='D') ,y_pred*(df_max-df_min)+df_min, color = 'y', label = '測試集預測') plt.plot(pd.date_range(start='2023-03-02', end='2023-03-11', freq='D') ,series_1, color = 'magenta',linestyle='-.', label = '未來預測') plt.legend() plt.subplot(3,1,2) plt.plot(test_set, color = 'b', label = '測試集') plt.plot(pd.date_range(start='2016-08-12', end='2023-03-01', freq='D') ,y_pred*(df_max-df_min)+df_min, color = 'y', label = '測試集預測') plt.plot(pd.date_range(start='2023-03-02', end='2023-03-11', freq='D') ,series_1, color = 'magenta', linestyle='-.',label = '未來預測') plt.legend() plt.subplot(3,1,3) plt.plot(test_set, color = 'b', label = '測試集') plt.plot(pd.date_range(start='2016-08-12', end='2023-03-01', freq='D') ,y_pred*(df_max-df_min)+df_min, color = 'y', label = '測試集預測') plt.plot(pd.date_range(start='2023-03-02', end='2023-03-11', freq='D') ,series_1, color = 'magenta',linestyle='-.', label = '未來預測') # 設置x軸范圍為2022年到未來預測的結束日期 plt.xlim(pd.Timestamp('2022-01-01'), pd.Timestamp('2023-03-11')) plt.legend() plt.show()

2.4 CNN-BiLSTM模型構建

from tensorflow.keras.layers import Conv1D, MaxPooling1D, Reshape, Flatten model_cnn_bilstm = Sequential() model_cnn_bilstm.add(Bidirectional(LSTM(128, activation='relu'), input_shape=(X_train.shape[1], X_train.shape[2]))) # 添加Reshape層將LSTM的輸出轉換為3維 model_cnn_bilstm.add(Reshape((256, 1))) model_cnn_bilstm.add(Conv1D(filters=64, kernel_size=7, activation='relu')) model_cnn_bilstm.add(MaxPooling1D(pool_size=2)) model_cnn_bilstm.add(Flatten()) # 將池化后的輸出展平成一維向量 model_cnn_bilstm.add(Dense(32, activation='relu')) model_cnn_bilstm.add(Dense(16, activation='relu')) model_cnn_bilstm.add(Dense(1)) model_cnn_bilstm.compile(optimizer='adam', loss='mse') history = model_cnn_bilstm.fit(X_train, y_train, epochs=50, batch_size=32, validation_data=(X_val, y_val)) plt.figure() plt.plot(history.history['loss'], c='b', label = 'loss') plt.plot(history.history['val_loss'], c='g', label = 'val_loss') plt.legend() plt.show()

y_pred = model_cnn_bilstm.predict(X_test) mse = metrics.mean_squared_error(y_test, np.array([i for arr in y_pred for i in arr])) rmse = np.sqrt(mse) mae = metrics.mean_absolute_error(y_test, np.array([i for arr in y_pred for i in arr])) from sklearn.metrics import r2_score r2 = r2_score(y_test, np.array([i for arr in y_pred for i in arr])) print("均方誤差 (MSE):", mse) print("均方根誤差 (RMSE):", rmse) print("平均絕對誤差 (MAE):", mae) print("擬合優度:", r2)

last_output = model_cnn_bilstm.predict(X_test)[-1] steps = 10 predicted = [] for i in range(steps): input_data = np.append(X_test[-1][1:], last_output).reshape(1, X_test.shape[1], X_test.shape[2]) next_output = model_cnn_bilstm.predict(input_data) predicted.append(next_output[0][0]) last_output = next_output[0] series_2 = np.array(predicted)*(df_max-df_min)+df_min plt.figure(figsize=(15,4), dpi =300) plt.subplot(3,1,1) plt.plot(train_set, color = 'c', label = '訓練集') plt.plot(val_set, color = 'r', label = '驗證集') plt.plot(test_set, color = 'b', label = '測試集') plt.plot(pd.date_range(start='2016-08-12', end='2023-03-01', freq='D') ,y_pred*(df_max-df_min)+df_min, color = 'y', label = '測試集預測') plt.plot(pd.date_range(start='2023-03-02', end='2023-03-11', freq='D') ,series_2, color = 'magenta',linestyle='-.', label = '未來預測') plt.legend() plt.subplot(3,1,2) plt.plot(test_set, color = 'b', label = '測試集') plt.plot(pd.date_range(start='2016-08-12', end='2023-03-01', freq='D') ,y_pred*(df_max-df_min)+df_min, color = 'y', label = '測試集預測') plt.plot(pd.date_range(start='2023-03-02', end='2023-03-11', freq='D') ,series_2, color = 'magenta',linestyle='-.', label = '未來預測') plt.legend() plt.subplot(3,1,3) plt.plot(test_set, color = 'b', label = '測試集') plt.plot(pd.date_range(start='2016-08-12', end='2023-03-01', freq='D') ,y_pred*(df_max-df_min)+df_min, color = 'y', label = '測試集預測') plt.plot(pd.date_range(start='2023-03-02', end='2023-03-11', freq='D') ,series_2, color = 'magenta',linestyle='-.', label = '未來預測') # 設置x軸范圍為2022年到未來預測的結束日期 plt.xlim(pd.Timestamp('2022-01-01'), pd.Timestamp('2023-03-11')) plt.legend() plt.show()