def __read_data__(self): self.scaler = StandardScaler() df_raw = pd.read_csv(os.path.join(self.root_path, self.data_path)) border1s = [0, 12*30*24 - self.seq_len, 12*30*24+4*30*24 - self.seq_len] border2s = [12*30*24, 12*30*24+4*30*24, 12*30*24+8*30*24] border1 = border1s[self.set_type] border2 = border2s[self.set_type] if self.features=='M' or self.features=='MS': cols_data = df_raw.columns[1:] df_data = df_raw[cols_data] elif self.features=='S': df_data = df_raw[[self.target]] if self.scale: train_data = df_data[border1s[0]:border2s[0]] self.scaler.fit(train_data.values) data = self.scaler.transform(df_data.values) else: data = df_data.values df_stamp = df_raw[['date']][border1:border2] df_stamp['date'] = pd.to_datetime(df_stamp.date) data_stamp = time_features(df_stamp, timeenc=self.timeenc, freq=self.freq) self.data_x = data[border1:border2] if self.inverse: self.data_y = df_data.values[border1:border2] else: self.data_y = data[border1:border2] self.data_stamp = data_stamp
def __read_data__(self): self.scaler = StandardScaler() df_raw = pd.read_csv(os.path.join(self.root_path, self.data_name)) # 0, # num of hours in a year - num of hours in 4 days, # num of hours in a year + num of hours in 4 months - num of hours in 4 days border1s = [0, 12*30*24 - self.seq_len, 12*30*24+4*30*24 - self.seq_len] # num of hours in a year, # num of hours in a year + num of hours in 4 months, # num of hours in a year + num of hours in 8 months border2s = [12*30*24, 12*30*24+4*30*24, 12*30*24+8*30*24] border1 = border1s[self.set_type] border2 = border2s[self.set_type] if self.features=='M' or self.features=='MS': cols_data = df_raw.columns[1:] df_data = df_raw[cols_data] elif self.features=='S': df_data = df_raw[[self.target]] # print(df_data.shape) if self.scale: train_data = df_data[border1s[0]:border2s[0]] self.scaler.fit(train_data.values) data = self.scaler.transform(df_data.values) else: data = df_data.values # retrieve one year's record df_stamp = df_raw[['date']][border1:border2] df_stamp['date'] = pd.to_datetime(df_stamp.date) if self.timeenc == 0: df_stamp['month'] = df_stamp.date.apply(lambda row: (row.month)) df_stamp['day'] = df_stamp.date.apply(lambda row: row.day) df_stamp['weekday'] = df_stamp.date.apply(lambda row: row.weekday()) df_stamp['hour'] = df_stamp.date.apply(lambda row: row.hour) data_stamp = df_stamp.drop(['date'], axis=1).values elif self.timeenc == 1: data_stamp = time_features(pd.to_datetime(df_stamp['date'].values), freq=self.freq) data_stamp = data_stamp.transpose(1,0) # print(df_stamp) # print(data_stamp) # x and y are identical here self.data_x = data[border1:border2] self.data_y = data[border1:border2] self.data_stamp = data_stamp
def __read_data__(self): self.scaler = StandardScaler() df_raw = pd.read_csv(os.path.join(self.root_path, self.data_path)) ''' df_raw.columns: ['date', ...(other features), target feature] ''' # cols = list(df_raw.columns); if self.cols: cols = self.cols.copy() cols.remove(self.target) else: cols = list(df_raw.columns) # print(cols) cols.remove(self.target) cols.remove('date') df_raw = df_raw[['date'] + cols + [self.target]] num_train = int(len(df_raw) * 0.7) num_test = int(len(df_raw) * 0.2) num_vali = len(df_raw) - num_train - num_test border1s = [ 0, num_train - self.seq_len, len(df_raw) - num_test - self.seq_len ] border2s = [num_train, num_train + num_vali, len(df_raw)] border1 = border1s[self.set_type] border2 = border2s[self.set_type] if self.features == 'M' or self.features == 'MS': cols_data = df_raw.columns[1:] df_data = df_raw[cols_data] elif self.features == 'S': df_data = df_raw[[self.target]] if self.scale: train_data = df_data[border1s[0]:border2s[0]] self.scaler.fit(train_data.values) data = self.scaler.transform(df_data.values) else: data = df_data.values df_stamp = df_raw[['date']][border1:border2] df_stamp['date'] = pd.to_datetime(df_stamp.date) data_stamp = time_features(df_stamp, timeenc=self.timeenc, freq=self.freq) self.data_x = data[border1:border2] if self.inverse: self.data_y = df_data.values[border1:border2] else: self.data_y = data[border1:border2] self.data_stamp = data_stamp
def __read_data__(self): self.scaler = StandardScaler() df_raw = pd.read_csv(os.path.join(self.root_path, self.data_path)) if self.delete_column_list: df_raw = df_raw.drop(self.delete_column_list, axis=1) if self.date_column: df_raw.rename(columns={self.date_column: 'date'},inplace = True) print(df_raw.columns) ''' df_raw.columns: ['date', ...(other features), target feature] ''' cols = list(df_raw.columns); cols.remove(self.target) df_raw = df_raw[cols+[self.target]] num_train = int(len(df_raw)*0.7) num_test = int(len(df_raw)*0.2) num_vali = len(df_raw) - num_train - num_test border1s = [0, num_train-self.seq_len, len(df_raw)-num_test-self.seq_len] border2s = [num_train, num_train+num_vali, len(df_raw)] border1 = border1s[self.set_type] border2 = border2s[self.set_type] if self.features=='M' or self.features=='MS': cols_data = df_raw.columns[1:] df_data = df_raw[cols_data] elif self.features=='S': df_data = df_raw[[self.target]] if self.scale: train_data = df_data[border1s[0]:border2s[0]] self.scaler.fit(train_data.values) data = self.scaler.transform(df_data.values) else: data = df_data.values df_stamp = df_raw[['date']][border1:border2] df_stamp['date'] = pd.to_datetime(df_stamp.date) print(df_stamp.head()) if self.timeenc==0: df_stamp['month'] = df_stamp.date.apply(lambda row:row.month,1) df_stamp['day'] = df_stamp.date.apply(lambda row:row.day,1) df_stamp['weekday'] = df_stamp.date.apply(lambda row:row.weekday(),1) df_stamp['hour'] = df_stamp.date.apply(lambda row:row.hour,1) data_stamp = df_stamp.drop(['date'],1).values elif self.timeenc==1: data_stamp = time_features(pd.to_datetime(df_stamp['date'].values), freq=self.freq) data_stamp = data_stamp.transpose(1,0) print(df_stamp.head()) self.data_x = data[border1:border2] self.data_y = data[border1:border2] self.data_stamp = data_stamp
def __read_data__(self): self.scaler = StandardScaler() df_raw = pd.read_csv(os.path.join(self.root_path, self.data_path)) ''' df_raw.columns: ['date', ...(other features), target feature] ''' if self.cols: cols = self.cols.copy() cols.remove(self.target) else: cols = list(df_raw.columns) cols.remove(self.target) cols.remove('date') df_raw = df_raw[['date'] + cols + [self.target]] # 予測では最後の値を使う border1 = len(df_raw) - self.seq_len border2 = len(df_raw) if self.features == 'M' or self.features == 'MS': cols_data = df_raw.columns[1:] df_data = df_raw[cols_data] elif self.features == 'S': df_data = df_raw[[self.target]] if self.scale: self.scaler.fit(df_data.values) data = self.scaler.transform(df_data.values) else: data = df_data.values tmp_stamp = df_raw[['date']][border1:border2] tmp_stamp['date'] = pd.to_datetime(tmp_stamp.date) pred_dates = pd.date_range(tmp_stamp.date.values[-1], periods=self.pred_len + 1, freq=self.freq) # priods 個数指定 df_stamp = pd.DataFrame(columns=['date']) df_stamp.date = list(tmp_stamp.date.values) + list(pred_dates[1:]) data_stamp = time_features(df_stamp, timeenc=self.timeenc, freq=self.freq[-1:]) self.data_x = data[border1:border2] if self.inverse: self.data_y = df_data.values[border1:border2] else: self.data_y = data[border1:border2] self.data_stamp = data_stamp
def __read_data__(self): self.scaler = StandardScaler() df_raw = pd.read_csv(os.path.join(self.root_path, self.data_path)) border1s = [ 0, 12 * 30 * 24 * 4 - self.seq_len, 12 * 30 * 24 * 4 + 4 * 30 * 24 * 4 - self.seq_len ] border2s = [ 12 * 30 * 24 * 4, 12 * 30 * 24 * 4 + 4 * 30 * 24 * 4, 12 * 30 * 24 * 4 + 8 * 30 * 24 * 4 ] border1 = border1s[self.set_type] border2 = border2s[self.set_type] if self.features == 'M' or self.features == 'MS': cols_data = df_raw.columns[1:] df_data = df_raw[cols_data] elif self.features == 'S': df_data = df_raw[[self.target]] if self.scale: train_data = df_data[border1s[0]:border2s[0]] self.scaler.fit(train_data.values) data = self.scaler.transform(df_data.values) else: data = df_data.values df_stamp = df_raw[['date']][border1:border2] df_stamp['date'] = pd.to_datetime(df_stamp.date) if self.timeenc == 0: df_stamp['month'] = df_stamp.date.apply(lambda row: row.month, 1) df_stamp['day'] = df_stamp.date.apply(lambda row: row.day, 1) df_stamp['weekday'] = df_stamp.date.apply( lambda row: row.weekday(), 1) df_stamp['hour'] = df_stamp.date.apply(lambda row: row.hour, 1) df_stamp['minute'] = df_stamp.date.apply(lambda row: row.minute, 1) df_stamp['minute'] = df_stamp.minute.map(lambda x: x // 15) data_stamp = df_stamp.drop(['date'], 1).values elif self.timeenc == 1: data_stamp = time_features(pd.to_datetime(df_stamp['date'].values), freq=self.freq) data_stamp = data_stamp.transpose(1, 0) self.data_x = data[border1:border2] self.data_y = data[border1:border2] self.data_stamp = data_stamp
def __read_data__(self): self.scaler = StandardScaler() df_raw = pd.read_csv(os.path.join(self.root_path, self.data_path)) ''' df_raw.columns: ['date', ...(other features), target feature] ''' cols = list(df_raw.columns); cols.remove(self.target); cols.remove('date') df_raw = df_raw[['date']+cols+[self.target]] border1 = len(df_raw)-self.seq_len border2 = len(df_raw) if self.features=='M' or self.features=='MS': cols_data = df_raw.columns[1:] df_data = df_raw[cols_data] elif self.features=='S': df_data = df_raw[[self.target]] if self.scale: self.scaler.fit(df_data.values) data = self.scaler.transform(df_data.values) else: data = df_data.values tmp_stamp = df_raw[['date']][border1:border2] tmp_stamp['date'] = pd.to_datetime(tmp_stamp.date) pred_dates = pd.date_range(tmp_stamp.date.values[-1], periods=self.pred_len+1, freq=self.freq) df_stamp = pd.DataFrame(columns = ['date']) df_stamp.date = list(tmp_stamp.date.values) + list(pred_dates[1:]) if self.timeenc==0: df_stamp['month'] = df_stamp.date.apply(lambda row:row.month,1) df_stamp['day'] = df_stamp.date.apply(lambda row:row.day,1) df_stamp['weekday'] = df_stamp.date.apply(lambda row:row.weekday(),1) df_stamp['hour'] = df_stamp.date.apply(lambda row:row.hour,1) data_stamp = df_stamp.drop(['date'],1).values elif self.timeenc==1: data_stamp = time_features(pd.to_datetime(df_stamp['date'].values), freq=self.freq[-1:]) data_stamp = data_stamp.transpose(1,0) self.data_x = data[border1:border2] self.data_y = data[border1:border2] self.data_stamp = data_stamp
def __read_data__(self): # __get_item__でデータを取得しやすくするための準備 self.scaler = StandardScaler() df_raw = pd.read_csv(os.path.join( self.root_path, self.data_path)) # ここでは二次元?? というか次元数がない # 12 month 30 day 24 hour border1s = [ 0, 12 * 30 * 24 - self.seq_len, 12 * 30 * 24 + 4 * 30 * 24 - self.seq_len ] # train の場合は0から一年 # val : 1年4ヶ月の96時点 # test : 一年4ヶ月から1年八ヶ月 border2s = [ 12 * 30 * 24, 12 * 30 * 24 + 4 * 30 * 24, 12 * 30 * 24 + 8 * 30 * 24 ] border1 = border1s[self.set_type] # 複数形 border2 = border2s[self.set_type] # 説明変数の数 multi or single 多変量か単変量か? if self.features == 'M' or self.features == 'MS': cols_data = df_raw.columns[1:] # 時刻の列いがい df_data = df_raw[cols_data] elif self.features == 'S': df_data = df_raw[[self.target]] if self.scale: # default True 正規化をするかしないか train_data = df_data[border1s[0]:border2s[0]] # trainなら0から2年 self.scaler.fit(train_data.values) # データの標準化 標準かをしないほうがいいのか まだしない # 正規化の実行 訓練データの平均と分散で正規化する 答えをカンニングしないということ? data = self.scaler.transform(df_data.values) else: data = df_data.values # データの取得 nd array # これは画像であるPIL image または ndarrayのdata「Height×Width×Channel」を # Tensor型のdata「Channel×Height×Width」に変換するというもので, # transという変数がその機能を持つことを意味する. # なぜChannelの順が入れ替わっているかというと,機械学習をしていく上でChannelが最初のほうが # 都合が良いからだと思ってもらって良い. # 今の状態でchannelって何?? df_stamp = df_raw[['date']][border1:border2] # 必要な行数の時刻を取得 df_stamp['date'] = pd.to_datetime(df_stamp.date) # 辞書で呼び出せるように?? # datatime型がnp.ndarray方になる # 二次元 時間方向 × その時刻の表現の埋め込み表現 # ある時刻に対してその位置埋め込み表現の長さはバラバラ # あるデータに対しては同じ data_stamp = time_features(df_stamp, timeenc=self.timeenc, freq=self.freq) # data_xとdata_yで何が違う?? self.data_x = data[border1:border2] # データ 二次元 if self.inverse: # default false self.data_y = df_data.values[border1:border2] else: self.data_y = data[border1:border2] # transformしていた : # していなかった : values[border1:border2] self.data_stamp = data_stamp
def __read_data__(self): self.scaler = StandardScaler() # 標準化のため df_raw = pd.read_csv(os.path.join(self.root_path, self.data_path)) ''' df_raw.columns: ['date', ...(other features), target feature] ''' # cols = list(df_raw.columns); # データの列に対して並び替えをする IndexはDatatime型にしない 列の'date'がindexになる # つまり自分のstepCountを使いたいなら'date'がindexになる if self.cols: cols = self.cols.copy() cols.remove(self.target) else: cols = list(df_raw.columns) cols.remove(self.target) cols.remove('date') df_raw = df_raw[['date'] + cols + [self.target]] num_train = int(len(df_raw) * 0.7) num_test = int(len(df_raw) * 0.2) num_vali = len(df_raw) - num_train - num_test # つまり 1 - 0.7 - 0.2 # 複数形のs # [0 訓練データまでのindex, validation 検証用データまでのindex, テストデータまでのindex] border1s = [ 0, num_train - self.seq_len, len(df_raw) - num_test - self.seq_len ] border2s = [num_train, num_train + num_vali, len(df_raw)] # 取り出したいデータの種類に合わせて border1 = border1s[self.set_type] # どのindexから border2 = border2s[self.set_type] # どのindexまでを取り出すのか if self.features == 'M' or self.features == 'MS': cols_data = df_raw.columns[1:] df_data = df_raw[cols_data] elif self.features == 'S': df_data = df_raw[[self.target]] if self.scale: # 標準化するかどうか train_data = df_data[border1s[0]:border2s[0]] # axis = 0 で平均, 分散を計算 self.scaler.fit(train_data.values) # 平均, 分散により標準化, dfのtransformではない data = self.scaler.transform(df_data.values) else: data = df_data.values df_stamp = df_raw[['date']][border1:border2] # dataframeからはドットで取り出すこともできる # indexはintで持っておいて, date列名にdatatime型で持っておく df_stamp['date'] = pd.to_datetime(df_stamp.date) # 最終的にmarkとして扱われる data_stamp = time_features(df_stamp, timeenc=self.timeenc, freq=self.freq) self.data_x = data[border1:border2] if self.inverse: self.data_y = df_data.values[border1:border2] else: self.data_y = data[border1:border2] self.data_stamp = data_stamp