read_data.py

import pandas as pd
import numpy as np

# read emoticon dataset
train_emoticon_df = pd.read_csv("datasets/train/train_emoticon.csv")
train_emoticon_X = train_emoticon_df['input_emoticon'].tolist()
train_emoticon_Y = train_emoticon_df['label'].tolist()

test_emoticon_X = pd.read_csv("datasets/test/test_emoticon.csv")['input_emoticon'].tolist()

# read text sequence dataset
train_seq_df = pd.read_csv("datasets/train/train_text_seq.csv")
train_seq_X = train_seq_df['input_str'].tolist()
train_seq_Y = train_seq_df['label'].tolist()

test_seq_X = pd.read_csv("datasets/test/test_text_seq.csv")['input_str'].tolist()



# read feature dataset
train_feat = np.load("datasets/train/train_feature.npz", allow_pickle=True)
train_feat_X = train_feat['features']
train_feat_Y = train_feat['label']

test_feat_X = np.load("datasets/test/test_feature.npz", allow_pickle=True)['features']


print(f"Train dataset size: ")
print(f"train_emoticon_X: {len(train_emoticon_X)} train_emoticon_Y: {len(train_emoticon_Y)}")
print(f"train_seq_X: {len(train_seq_X)} train_seq_Y: {len(train_seq_Y)}")
print(f"train_feat_X: {train_feat_X.shape} train_feat_Y: {train_feat_Y.shape}")


print()
print("Test dataset size: ")
print(f"test_emoticon_X: {len(test_emoticon_X)}")
print(f"test_seq_X: {len(test_seq_X)} ")
print(f"test_feat_X: {test_feat_X.shape}")