From 43845ba362672d1d4cbcd968f58439cdbe48224a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=83=91=E9=9F=B6=E5=9D=A4?= <2509165013@student.example.com> Date: Thu, 30 Apr 2026 15:57:10 +0800 Subject: [PATCH] =?UTF-8?q?=E4=B8=8A=E4=BC=A0=E6=96=87=E4=BB=B6=E8=87=B3?= =?UTF-8?q?=20/?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- config.py | 80 +-- dataset.py | 572 ++++++++++---------- main.py | 68 +-- model_mlp_tfidf_weighted_0430_145915_b1.npy | Bin 0 -> 656 bytes model_mlp_tfidf_weighted_0430_145915_b2.npy | Bin 0 -> 152 bytes 5 files changed, 360 insertions(+), 360 deletions(-) create mode 100644 model_mlp_tfidf_weighted_0430_145915_b1.npy create mode 100644 model_mlp_tfidf_weighted_0430_145915_b2.npy diff --git a/config.py b/config.py index 12a552d..60c4d14 100644 --- a/config.py +++ b/config.py @@ -1,40 +1,40 @@ -# -*- coding: utf-8 -*- -""" -配置文件 - 所有超参数集中管理 - -设计思路： -将超参数分门别类，学生可以单独修改某一类而不会影响其他 -""" - -# ==================== 数据相关 ==================== -DATA_DIR = 'data/ChnSentiCorp' # 数据集路径 -MAX_FEATURES = 3000 # 词表最大容量 -MAX_SEQ_LEN = 100 # 句子最大长度（词数） -VECTORIZER_TYPE = 'tfidf' # 'tfidf' 或 'bow'（向量化方式） - -# ==================== 模型相关 ==================== -MODEL_TYPE = 'mlp' # 'mlp' 或 'lr'（模型类型） -HIDDEN_SIZE = 64 # MLP隐藏层大小（LR忽略） -NUM_CLASSES = 2 # 类别数（正面/负面二分类） -KEEP_PROB = 1.0 # Dropout保留概率（LR忽略，设为1即可） - -# ==================== 训练相关 ==================== -LEARNING_RATE = 0.05 # 学习率 -NUM_EPOCHS = 100 # 训练轮数 -BATCH_SIZE = 64 # 批次大小 - -# ==================== 类别权重（解决数据不平衡问题）==================== -USE_CLASS_WEIGHT = True # True=启用类别权重, False=不启用（对比用） -# 权重计算公式: n_samples / (n_classes * n_class_i) -# 正面评论多所以权重小，负面评论少所以权重大 -CLASS_WEIGHT_POS = 0.73 # 正面类权重（自动计算） -CLASS_WEIGHT_NEG = 1.58 # 负面类权重（自动计算） - -# ==================== 实验相关 ==================== -RUN_COMPARISON = False # True=运行对比实验, False=运行单个模型 -COMPARE_MODELS = ['lr', 'mlp'] # 要对比的模型列表 -COMPARE_VECTORS = ['bow', 'tfidf'] # 要对比的向量化方式 - -# ==================== 其他 ==================== -RANDOM_SEED = 42 # 随机种子（保证可复现） -VERBOSE = True # 打印详细日志 +# -*- coding: utf-8 -*- +""" +配置文件 - 所有超参数集中管理 + +设计思路： +将超参数分门别类，学生可以单独修改某一类而不会影响其他 +""" + +# ==================== 数据相关 ==================== +DATA_DIR = 'data/ChnSentiCorp' # 数据集路径 +MAX_FEATURES = 3000 # 词表最大容量 +MAX_SEQ_LEN = 100 # 句子最大长度（词数） +VECTORIZER_TYPE = 'tfidf' # 'tfidf' 或 'bow'（向量化方式） + +# ==================== 模型相关 ==================== +MODEL_TYPE = 'mlp' # 'mlp' 或 'lr'（模型类型） +HIDDEN_SIZE = 66 # MLP隐藏层大小（LR忽略） +NUM_CLASSES = 3 # 类别数（正面/负面二分类） +KEEP_PROB = 1.0 # Dropout保留概率（LR忽略，设为1即可） + +# ==================== 训练相关 ==================== +LEARNING_RATE = 0.1 # 学习率 +NUM_EPOCHS = 50 # 训练轮数 +BATCH_SIZE = 55 # 批次大小 + +# ==================== 类别权重（解决数据不平衡问题）==================== +USE_CLASS_WEIGHT = True # True=启用类别权重, False=不启用（对比用） +# 权重计算公式: n_samples / (n_classes * n_class_i) +# 正面评论多所以权重小，负面评论少所以权重大 +CLASS_WEIGHT_POS = 0.1 # 正面类权重（自动计算） +CLASS_WEIGHT_NEG = 1.66 # 负面类权重（自动计算） + +# ==================== 实验相关 ==================== +RUN_COMPARISON = False # True=运行对比实验, False=运行单个模型 +COMPARE_MODELS = ['lr', 'mlp'] # 要对比的模型列表 +COMPARE_VECTORS = ['bow', 'tfidf'] # 要对比的向量化方式 + +# ==================== 其他 ==================== +RANDOM_SEED = 42 # 随机种子（保证可复现） +VERBOSE = True # 打印详细日志 diff --git a/dataset.py b/dataset.py index e554362..4f4163e 100644 --- a/dataset.py +++ b/dataset.py @@ -1,286 +1,286 @@ -# -*- coding: utf-8 -*- -""" -数据加载与向量化模块 - -支持两种向量化方法： -1. BoW (Bag of Words) - 词频向量 -2. TF-IDF - 词频-逆文档频率向量 - -TF-IDF 的优势： -- 降低常见词（如"的"、"是"）的权重 -- 提升罕见词的信息量 -- 通常效果优于简单BoW -""" - -import os -import re -import csv -import math -import jieba -import numpy as np -from collections import Counter - -try: - import urllib.request - import ssl - DOWNLOAD_AVAILABLE = True -except ImportError: - DOWNLOAD_AVAILABLE = False - - -DATASET_URL = "https://raw.githubusercontent.com/SophonPlus/ChineseNlpCorpus/master/datasets/ChnSentiCorp_htl_all/ChnSentiCorp_htl_all.csv" - - -def download_dataset(data_dir): - """下载数据集（如果不存在）""" - csv_path = os.path.join(data_dir, 'ChnSentiCorp_htl_all.csv') - - if os.path.exists(csv_path): - print(f"数据已存在: {csv_path}") - return True - - if not DOWNLOAD_AVAILABLE: - return False - - print("正在下载数据集...") - ssl_context = ssl.create_default_context() - ssl_context.check_hostname = False - ssl_context.verify_mode = ssl.CERT_NONE - - try: - request = urllib.request.Request(DATASET_URL, headers={'User-Agent': 'Mozilla/5.0'}) - response = urllib.request.urlopen(request, timeout=120, context=ssl_context) - os.makedirs(data_dir, exist_ok=True) - with open(csv_path, 'wb') as f: - f.write(response.read()) - print(f"下载完成: {csv_path}") - return True - except Exception as e: - print(f"下载失败: {e}") - return False - - -def load_raw_data(data_dir): - """加载原始数据""" - csv_path = os.path.join(data_dir, 'ChnSentiCorp_htl_all.csv') - texts, labels = [], [] - - with open(csv_path, 'r', encoding='utf-8') as f: - reader = csv.reader(f) - for row in reader: - if len(row) < 2: - continue - try: - label = int(row[0]) - review = row[1].strip() - if review: - texts.append(review) - labels.append(label) - except (ValueError, IndexError): - continue - - return texts, np.array(labels) - - -def tokenize(text): - """中文分词""" - text = re.sub(r'[^\u4e00-\u9fa5a-zA-Z]', ' ', text) - words = jieba.lcut(text) - return [w for w in words if len(w) > 1] - - -# ==================== 向量化器 ==================== - -class BaseVectorizer: - """向量化器基类""" - def fit(self, texts): pass - def transform(self, texts): pass - def fit_transform(self, texts): pass - - -class BoWVectorizer(BaseVectorizer): - """ - 词袋模型 (Bag of Words) - - 原理：统计每个词在文本中出现的次数 - 向量维度 = 词表大小 - 每个维度 = 该词在本文本中出现的次数 - """ - - def __init__(self, max_features, max_seq_len): - self.max_features = max_features - self.max_seq_len = max_seq_len - self.vocab = {} - self.doc_freq = {} # 文档频率 - self.num_docs = 0 - - def fit(self, texts): - """构建词表（基于词频）""" - counter = Counter() - doc_counter = Counter() # 统计包含该词的文档数 - - for text in texts: - words = tokenize(text) - unique_words = set(words) - counter.update(words) - for w in unique_words: - doc_counter[w] += 1 - - self.num_docs = len(texts) - - # 取最高频的词 - most_common = counter.most_common(self.max_features) - self.vocab = {word: idx for idx, (word, _) in enumerate(most_common)} - - # 记录文档频率（用于TF-IDF） - self.doc_freq = {w: doc_counter[w] for w in self.vocab} - - print(f" BoW词表大小: {len(self.vocab)}") - return self - - def transform(self, texts): - """将文本转换为词频向量""" - vectors = [] - for text in texts: - words = tokenize(text) - freq = [0] * self.max_seq_len - for i, word in enumerate(words[:self.max_seq_len]): - if word in self.vocab: - freq[i] = 1 # 二值（出现=1，不出现=0） - vectors.append(freq) - return np.array(vectors, dtype=np.float32) - - def fit_transform(self, texts): - self.fit(texts) - return self.transform(texts) - - -class TFIDFVectorizer(BaseVectorizer): - """ - TF-IDF 向量器 - - 原理： - - TF(词频) = 词在本文本中出现的次数 - - IDF(逆文档频率) = log(总文档数 / 包含该词的文档数) - - TF-IDF = TF × IDF - - 优势： - - 降低常见无意义词的权重（如"的"、"是"） - - 提升罕见但有信息量的词 - """ - - def __init__(self, max_features, max_seq_len): - self.max_features = max_features - self.max_seq_len = max_seq_len - self.vocab = {} - self.idf = {} # 存储每个词的IDF值 - self.num_docs = 0 - - def fit(self, texts): - """构建词表并计算IDF""" - counter = Counter() - doc_counter = Counter() - - for text in texts: - words = tokenize(text) - unique_words = set(words) - counter.update(words) - for w in unique_words: - doc_counter[w] += 1 - - self.num_docs = len(texts) - - # 计算每个词的IDF - # IDF = log(总文档数 / 包含该词的文档数) - idf_values = {} - for word, df in doc_counter.items(): - idf_values[word] = math.log(self.num_docs / (df + 1)) + 1 # 加1防零 - - # 取IDF值最高的词（信息量最大的词） - sorted_words = sorted(idf_values.items(), key=lambda x: x[1], reverse=True) - self.vocab = {word: idx for idx, (word, _) in enumerate(sorted_words[:self.max_features])} - - # 保存IDF值 - self.idf = {word: idf_values[word] for word in self.vocab} - - print(f" TF-IDF词表大小: {len(self.vocab)}") - print(f" 平均IDF: {np.mean(list(self.idf.values())):.3f}") - return self - - def transform(self, texts): - """将文本转换为TF-IDF向量""" - vectors = [] - for text in texts: - words = tokenize(text) - - # 计算TF - tf = Counter(words) - tf_sum = len(words) if words else 1 - - # 生成向量 - vec = [0.0] * self.max_seq_len - for i, word in enumerate(words[:self.max_seq_len]): - if word in self.vocab: - # TF × IDF - vec[i] = (tf[word] / tf_sum) * self.idf.get(word, 0) - vectors.append(vec) - - return np.array(vectors, dtype=np.float32) - - def fit_transform(self, texts): - self.fit(texts) - return self.transform(texts) - - -def load_data(data_dir, max_features, max_seq_len, vectorizer_type='tfidf'): - """ - 加载并向量化数据 - - 参数： - - vectorizer_type: 'tfidf' 或 'bow' - """ - if not download_dataset(data_dir): - raise RuntimeError("数据加载失败，请检查网络或手动下载数据集") - - print("正在加载数据...") - texts, labels = load_raw_data(data_dir) - print(f"总评论数: {len(texts)}, 正面: {sum(labels)}, 负面: {len(labels) - sum(labels)}") - - # 选择向量化器 - if vectorizer_type == 'tfidf': - vectorizer = TFIDFVectorizer(max_features, max_seq_len) - vec_name = "TF-IDF" - else: - vectorizer = BoWVectorizer(max_features, max_seq_len) - vec_name = "BoW" - - print(f"正在使用{vec_name}向量化...") - X = vectorizer.fit_transform(texts) - y = labels - - # 打乱并划分 - np.random.seed(42) - indices = np.random.permutation(len(X)) - X = X[indices] - y = y[indices] - - split_idx = int(len(X) * 0.8) - X_train, X_test = X[:split_idx], X[split_idx:] - y_train, y_test = y[:split_idx], y[split_idx:] - - print(f"训练集: {len(X_train)}条, 测试集: {len(X_test)}条") - - return X_train, y_train, X_test, y_test, vectorizer - - -if __name__ == '__main__': - # 测试 - print("=" * 60) - print("测试 TF-IDF 向量化") - print("=" * 60) - X_train, y_train, X_test, y_test, vec = load_data( - 'data/ChnSentiCorp', max_features=3000, max_seq_len=100, - vectorizer_type='tfidf' - ) - print(f"\nX_train shape: {X_train.shape}") - print(f"X_train sample (前5个特征): {X_train[0][:5]}") +# -*- coding: utf-8 -*- +""" +数据加载与向量化模块 + +支持两种向量化方法： +1. BoW (Bag of Words) - 词频向量 +2. TF-IDF - 词频-逆文档频率向量 + +TF-IDF 的优势： +- 降低常见词（如"的"、"是"）的权重 +- 提升罕见词的信息量 +- 通常效果优于简单BoW +""" + +import os +import re +import csv +import math +import jieba +import numpy as np +from collections import Counter + +try: + import urllib.request + import ssl + DOWNLOAD_AVAILABLE = True +except ImportError: + DOWNLOAD_AVAILABLE = False + + +DATASET_URL = "https://raw.githubusercontent.com/SophonPlus/ChineseNlpCorpus/master/datasets/ChnSentiCorp_htl_all/ChnSentiCorp_htl_all.csv" + + +def download_dataset(data_dir): + """下载数据集（如果不存在）""" + csv_path = os.path.join(data_dir, 'ChnSentiCorp_htl_all.csv') + + if os.path.exists(csv_path): + print(f"数据已存在: {csv_path}") + return True + + if not DOWNLOAD_AVAILABLE: + return False + + print("正在下载数据集...") + ssl_context = ssl.create_default_context() + ssl_context.check_hostname = False + ssl_context.verify_mode = ssl.CERT_NONE + + try: + request = urllib.request.Request(DATASET_URL, headers={'User-Agent': 'Mozilla/5.0'}) + response = urllib.request.urlopen(request, timeout=120, context=ssl_context) + os.makedirs(data_dir, exist_ok=True) + with open(csv_path, 'wb') as f: + f.write(response.read()) + print(f"下载完成: {csv_path}") + return True + except Exception as e: + print(f"下载失败: {e}") + return False + + +def load_raw_data(data_dir): + """加载原始数据""" + csv_path = os.path.join(data_dir, 'ChnSentiCorp_htl_all.csv') + texts, labels = [], [] + + with open(csv_path, 'r', encoding='utf-8') as f: + reader = csv.reader(f) + for row in reader: + if len(row) < 2: + continue + try: + label = int(row[0]) + review = row[1].strip() + if review: + texts.append(review) + labels.append(label) + except (ValueError, IndexError): + continue + + return texts, np.array(labels) + + +def tokenize(text): + """中文分词""" + text = re.sub(r'[^\u4e00-\u9fa5a-zA-Z]', ' ', text) + words = jieba.lcut(text) + return [w for w in words if len(w) > 1] + + +# ==================== 向量化器 ==================== + +class BaseVectorizer: + """向量化器基类""" + def fit(self, texts): pass + def transform(self, texts): pass + def fit_transform(self, texts): pass + + +class BoWVectorizer(BaseVectorizer): + """ + 词袋模型 (Bag of Words) + + 原理：统计每个词在文本中出现的次数 + 向量维度 = 词表大小 + 每个维度 = 该词在本文本中出现的次数 + """ + + def __init__(self, max_features, max_seq_len): + self.max_features = max_features + self.max_seq_len = max_seq_len + self.vocab = {} + self.doc_freq = {} # 文档频率 + self.num_docs = 0 + + def fit(self, texts): + """构建词表（基于词频）""" + counter = Counter() + doc_counter = Counter() # 统计包含该词的文档数 + + for text in texts: + words = tokenize(text) + unique_words = set(words) + counter.update(words) + for w in unique_words: + doc_counter[w] += 1 + + self.num_docs = len(texts) + + # 取最高频的词 + most_common = counter.most_common(self.max_features) + self.vocab = {word: idx for idx, (word, _) in enumerate(most_common)} + + # 记录文档频率（用于TF-IDF） + self.doc_freq = {w: doc_counter[w] for w in self.vocab} + + print(f" BoW词表大小: {len(self.vocab)}") + return self + + def transform(self, texts): + """将文本转换为词频向量""" + vectors = [] + for text in texts: + words = tokenize(text) + freq = [0] * self.max_seq_len + for i, word in enumerate(words[:self.max_seq_len]): + if word in self.vocab: + freq[i] = 1 # 二值（出现=1，不出现=0） + vectors.append(freq) + return np.array(vectors, dtype=np.float32) + + def fit_transform(self, texts): + self.fit(texts) + return self.transform(texts) + + +class TFIDFVectorizer(BaseVectorizer): + """ + TF-IDF 向量器 + + 原理： + - TF(词频) = 词在本文本中出现的次数 + - IDF(逆文档频率) = log(总文档数 / 包含该词的文档数) + - TF-IDF = TF × IDF + + 优势： + - 降低常见无意义词的权重（如"的"、"是"） + - 提升罕见但有信息量的词 + """ + + def __init__(self, max_features, max_seq_len): + self.max_features = max_features + self.max_seq_len = max_seq_len + self.vocab = {} + self.idf = {} # 存储每个词的IDF值 + self.num_docs = 0 + + def fit(self, texts): + """构建词表并计算IDF""" + counter = Counter() + doc_counter = Counter() + + for text in texts: + words = tokenize(text) + unique_words = set(words) + counter.update(words) + for w in unique_words: + doc_counter[w] += 1 + + self.num_docs = len(texts) + + # 计算每个词的IDF + # IDF = log(总文档数 / 包含该词的文档数) + idf_values = {} + for word, df in doc_counter.items(): + idf_values[word] = math.log(self.num_docs / (df + 1)) + 1 # 加1防零 + + # 取IDF值最高的词（信息量最大的词） + sorted_words = sorted(idf_values.items(), key=lambda x: x[1], reverse=True) + self.vocab = {word: idx for idx, (word, _) in enumerate(sorted_words[:self.max_features])} + + # 保存IDF值 + self.idf = {word: idf_values[word] for word in self.vocab} + + print(f" TF-IDF词表大小: {len(self.vocab)}") + print(f" 平均IDF: {np.mean(list(self.idf.values())):.3f}") + return self + + def transform(self, texts): + """将文本转换为TF-IDF向量""" + vectors = [] + for text in texts: + words = tokenize(text) + + # 计算TF + tf = Counter(words) + tf_sum = len(words) if words else 1 + + # 生成向量 + vec = [0.0] * self.max_seq_len + for i, word in enumerate(words[:self.max_seq_len]): + if word in self.vocab: + # TF × IDF + vec[i] = (tf[word] / tf_sum) * self.idf.get(word, 0) + vectors.append(vec) + + return np.array(vectors, dtype=np.float32) + + def fit_transform(self, texts): + self.fit(texts) + return self.transform(texts) + + +def load_data(data_dir, max_features, max_seq_len, vectorizer_type='tfidf'): + """ + 加载并向量化数据 + + 参数： + - vectorizer_type: 'tfidf' 或 'bow' + """ + if not download_dataset(data_dir): + raise RuntimeError("数据加载失败，请检查网络或手动下载数据集") + + print("正在加载数据...") + texts, labels = load_raw_data(data_dir) + print(f"总评论数: {len(texts)}, 正面: {sum(labels)}, 负面: {len(labels) - sum(labels)}") + + # 选择向量化器 + if vectorizer_type == 'tfidf': + vectorizer = TFIDFVectorizer(max_features, max_seq_len) + vec_name = "TF-IDF" + else: + vectorizer = BoWVectorizer(max_features, max_seq_len) + vec_name = "BoW" + + print(f"正在使用{vec_name}向量化...") + X = vectorizer.fit_transform(texts) + y = labels + + # 打乱并划分 + np.random.seed(42) + indices = np.random.permutation(len(X)) + X = X[indices] + y = y[indices] + + split_idx = int(len(X) * 0.8) + X_train, X_test = X[:split_idx], X[split_idx:] + y_train, y_test = y[:split_idx], y[split_idx:] + + print(f"训练集: {len(X_train)}条, 测试集: {len(X_test)}条") + + return X_train, y_train, X_test, y_test, vectorizer + + +if __name__ == '__main__': + # 测试 + print("=" * 60) + print("测试 TF-IDF 向量化") + print("=" * 60) + X_train, y_train, X_test, y_test, vec = load_data( + 'data/ChnSentiCorp', max_features=3000, max_seq_len=100, + vectorizer_type='tfidf' + ) + print(f"\nX_train shape: {X_train.shape}") + print(f"X_train sample (前5个特征): {X_train[0][:5]}") diff --git a/main.py b/main.py index eaeaadc..2dbbe1c 100644 --- a/main.py +++ b/main.py @@ -1,34 +1,34 @@ -# -*- coding: utf-8 -*- -""" -主程序入口 - -使用方式： - -1. 运行单个模型（默认）： - python main.py - - 修改 config.py 中的 MODEL_TYPE 和 VECTORIZER_TYPE 来切换配置 - -2. 运行对比实验： - 修改 config.py 中 RUN_COMPARISON = True - - 这会依次运行： - - 实验1: BoW vs TF-IDF (固定LR模型) - - 实验2: LR vs MLP (固定TF-IDF) - - 实验3: 不同学习率对比 - - 实验4: 不同隐藏层大小对比 - - 最后输出汇总报告 -""" - -from train import main - -if __name__ == '__main__': - print("\n" + "=" * 70) - print("文本分类实验 - 纯NumPy实现") - print("数据集: ChnSentiCorp (中文酒店评论)") - print("模型: Logistic Regression / MLP") - print("向量化: BoW / TF-IDF") - print("=" * 70 + "\n") - - main() +# -*- coding: utf-8 -*- +""" +主程序入口 + +使用方式： + +1. 运行单个模型（默认）： + python main.py + + 修改 config.py 中的 MODEL_TYPE 和 VECTORIZER_TYPE 来切换配置 + +2. 运行对比实验： + 修改 config.py 中 RUN_COMPARISON = True + + 这会依次运行： + - 实验1: BoW vs TF-IDF (固定LR模型) + - 实验2: LR vs MLP (固定TF-IDF) + - 实验3: 不同学习率对比 + - 实验4: 不同隐藏层大小对比 + + 最后输出汇总报告 +""" + +from train import main + +if __name__ == '__main__': + print("\n" + "=" * 70) + print("文本分类实验 - 纯NumPy实现") + print("数据集: ChnSentiCorp (中文酒店评论)") + print("模型: Logistic Regression / MLP") + print("向量化: BoW / TF-IDF") + print("=" * 70 + "\n") + + main() diff --git a/model_mlp_tfidf_weighted_0430_145915_b1.npy b/model_mlp_tfidf_weighted_0430_145915_b1.npy new file mode 100644 index 0000000000000000000000000000000000000000..65867c652d64eab2116c7512373c8c6ff0e3c8d8 GIT binary patch literal 656 zcmbR27wQ`j$;eQ~P_3SlTAW;@Zl$1ZlV+i=qoAIaUsO_*m=~X4l#&V(cT3DEP6dh= zXCxM+0{I$dW;&WW3bhL41Fj^|_2P4%bl68<+q>w&gy;7Atj>wpsdm~cxy(Lw*D+%M zdw03HM_e-Y{}G=#D~3N{fAvqsi04Od*%x#j$XMNW)P9kIorLz%WP1Ze`K&tI{rj^v z*7hrQ9e$1&_ ze9qovgL8`D1=s!NOTKP$venvO`>0L2q3419k9FBB-Rv*zlf|rC16_OU*O{MWotNKk zzt@BBhVH)>`%}%D@2yuI-(SQrZ+Bkqk^P;YRPk zmk^^@+!O5$Uf%v7VJ^OZ)^`oYBirBE&yZiHTgFmipR(SmWzCh4{mgToNKeZ;yg%M? z>Y>|9+U>V&FYvMd+-9HHsbcf7a`S!*?#NyHy*BL+NQs;mx!l3NHi0SP-CNiF(JDV4 z_sE~IZ$F^BeZRnadwaFO$*;Rk*jozByfr!H$bPx`9h!d}ocHrt+n<_Jl(_%)?C&)v z<4)RJ{g(N2GU3?%g%4sYqwid_Pr21|SZC3${m&O{y*+8y?){gz-_2Cv+O=PgFIgZ! H?#O-sF_t1; literal 0 HcmV?d00001 diff --git a/model_mlp_tfidf_weighted_0430_145915_b2.npy b/model_mlp_tfidf_weighted_0430_145915_b2.npy new file mode 100644 index 0000000000000000000000000000000000000000..27f9d62b325c717a03b73f708b07135b57b47bb2 GIT binary patch literal 152 zcmbR27wQ`j$;eQ~P_3SlTAW;@Zl$1ZlV+i=qoAIaUsO_*m=~X4l#&V(cT3DEP6dh= uXCxM+0{I%oI+{8PwF(pfuBKAvh=S1f_RCkeoT{pNWFPByB8