keras_nn.py 文件源码

def getFeatureMatrix(self, df):
        if cfg.input_type == "text":
            from keras.preprocessing.text import one_hot
            from keras.preprocessing.sequence import pad_sequences
            textconverter = lambda x: x
            if sys.version_info[0] == 2:
                textconverter = lambda x: x.encode("utf-8")
            X = pad_sequences(
                df.apply(lambda row: one_hot(textconverter(row[self.text_field]), self.vocabulary_size), axis=1),
                self.word_limit)
            self.fields = [cfg.text_field]
            self.input_shape = (self.word_limit,)
        elif self.objective == "time_series":
            num_series = 1+len(self.fields)
            data = [df[self.target].tolist()]
            num_rows = len(data[0])

            for field in self.fields:
                data.append(df[field].tolist())

            instances = []
            target_instances = []

            for index in range(num_rows - (self.window_size+1)):
                windows = []
                for windex in range(self.window_size):
                    series = []
                    for sindex in range(num_series):
                        series.append(data[sindex][index+windex])
                    windows.append(series)
                target_window = []
                for sindex in range(num_series):
                    target_window.append(data[sindex][index + self.window_size])
                instances.append(windows)
                target_instances.append(target_window)

            X = np.array(instances)
            self.seqtargets = np.array(target_instances)

            X = np.reshape(X, (X.shape[0], self.window_size, num_series))
            print(X.shape)
            self.input_shape = (self.window_size, num_series)
        else:
            X = df.as_matrix(self.fields)
            self.input_shape = (len(self.fields),)

        self.model_metadata["predictors"] = self.fields

        return X