# 必要なライブラリのインポート import pandas as pd import numpy as np from sklearn.model_selection import train_test_split from sklearn.preprocessing import LabelEncoder from keras.models import Sequential from keras.layers import Dense # データの読み込み # data = pd.read_csv(‘your_data.csv’) # データのファイルパスを指定してください # データの読み込み data = pd.read_csv(r’/home/share/temp/shipping_size_traning.csv’) # カテゴリカル変数のエンコード category_label_encoder = LabelEncoder() data[‘category_encoded’] = category_label_encoder.fit_transform(data[‘category’]) product_name_label_encoder = LabelEncoder() data[‘product_name_encoded’] = product_name_label_encoder.fit_transform(data[‘product_name’]) product_maker_number_label_encoder = LabelEncoder() data[‘product_maker_number_encoded’] = product_maker_number_label_encoder.fit_transform(data[‘product_maker_number’]) # 目的変数と説明変数の分割 X = data.drop([‘size’, ‘product_name’,”product_maker_number”, ‘original_product_code’], axis=1) # 説明変数 y = data[‘size’] # 目的変数 # 訓練データとテストデータに分割 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) X_train=X_train.astype(float) X_test=X_test.astype(float) y_train=y_train.astype(float) y_test=y_test.astype(float) # モデルの構築 model = Sequential([ Dense(64, activation=’relu’, input_shape=(X_train.shape[1],)), Dense(64, activation=’relu’), Dense(len(np.unique(y)), activation=’softmax’) ]) # モデルのコンパイル model.compile(optimizer=’adam’, loss=’sparse_categorical_crossentropy’, metrics=[‘accuracy’]) # モデルのトレーニング model.fit(X_train, y_train, epochs=10, batch_size=32, validation_data=(X_test, y_test)) # モデルの評価 loss, accuracy = model.evaluate(X_test, y_test) print(“Test Loss:”, loss) print(“Test Accuracy:”, accuracy)