文本分类计算机毕设+论文完整的 

import pandas as pd
import numpy as np
from collections import Counter
import re
import jieba
from tqdm import tqdm
from sklearn.metrics import roc_curve, auc
import joblib
import gensim
from sklearn.svm import SVC
from gensim.models import KeyedVectors
from gensim.models import Word2Vec
from gensim.models.word2vec import LineSentence
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
#V wqqpython
plt.rcParams["font.sans-serif"] = ['Simhei']
plt.rcParams["axes.unicode_minus"] = False
# gensim==4.2.0
def data_process():# 数据预处理函数
    data=pd.read_csv("nCoV_100k_train.labled.csv")
    # print(data.columns)
    data_sorce=data['微博中文内容'].values
    data_label=data['情感倾向'].values
    # print(len(data_sorce))
    # print(Counter(data_label))

    train_text_data=[]
    train_text_data_label=[]

    train_text_data_0=[]
    train_text_data_1=[]
    train_text_data__1=[]

    train_text_data_1_label=[]
    train_text_data_0_label=[]
    train_text_data__1_label=[]

    sum_idx = 0# 计数器
    for idx,line in enumerate(data_sorce):
        if str(data_label[idx])=='0':
            if len(train_text_data_0)<11800:
                line1=re.findall(u'[\u4e00-\u9fa5]',str(line))
                if len(line1)>20:
                    sum_idx+=1
                    train_text_data_0.append(line)
                    train_text_data_0_label.append(int(data_label[idx])+1)

        if str(data_label[idx]) == '1':
            if len(train_text_data_1)<11800:
                line1 = re.findall(u'[\u4e00-\u9fa5]', str(line))
                if len(line1) > 20:
                        sum_idx += 1
                        train_text_data_1.append(line)
                        train_text_data_1_label.append(int(data_label[idx])+1)

        if str(data_label[idx]) == '-1':
            if len(train_text_data__1)<11800:
                line1 = re.findall(u'[\u4e00-\u9fa5]', str(line))
                if len(line1) > 20:
                        sum_idx += 1
                        train_text_data__1.append(line)
                        train_text_data__1_label.append(int(data_label[idx])+1)# 不允许出现负数
        if sum_idx==35000:
                break
    train_text_data=train_text_data_0+train_text_data_1+train_text_data__1
    train_text_data_label=train_text_data_0_label+train_text_data_1_label+train_text_data__1_label
    print(Counter(train_text_data_label))
    return train_text_data,train_text_data_label
train_text_data,train_text_data_label=data_process()
# 使用word2vec之前先进行word2vec的语料库训练 只需要训练一次 就可以

model = Word2Vec(LineSentence(open('word2vec_txt.txt', 'r', encoding='utf-8')), sg=0, vector_size=64, window=3, min_count=3, workers=4)
# 模型保存
model.save('test.model')

# 通过模型加载词向量(recommend)
model_vec = gensim.models.Word2Vec.load('test.model')
dic = model_vec.wv.index_to_key
#print(dic)
#print(len(dic))

x_train,x_test,y_train,y_test = train_test_split(train_text_data,train_text_data_label,test_size=0.2)
train_vec=[]
train_vec_label=[]
test_vec=[]
test_vec_label=[]
for idx,line in enumerate(x_train):
    """
     训练急 构建向量：对每个句子的所有词向量取均值，生成一个句子的vector
    """
    vec = np.zeros(64).reshape((1, 64))
    count = 0
    for word in jieba.cut(line , cut_all=False):
        try:
            vec = vec + model.wv[word].reshape((1,64))
            count += 1
        except KeyError:
            continue
    if count != 0:
        vec /= count
    train_vec.append(vec[0])
    train_vec_label.append(y_train[idx])

for idx,line in enumerate(x_test):
    """
     训练集 构建向量：对每个句子的所有词向量取均值，生成一个句子的vector
    """
    vec = np.zeros(64).reshape((1, 64))
    count = 0
    for word in jieba.cut(line , cut_all=False):
        try:
            vec = vec + model.wv[word].reshape((1,64))
            count += 1
        except KeyError:
            continue
    if count != 0:
        vec /= count
    test_vec.append(vec[0])
    test_vec_label.append(y_test[idx])

from sklearn.naive_bayes import GaussianNB
from xgboost import XGBRegressor,XGBClassifier
from lightgbm import LGBMClassifier
clf = LGBMClassifier()
clf.fit(train_vec, y_train)

joblib.dump(clf, '../GaussianNB.pkl', compress=3)
y_pred = clf.predict(test_vec)
from sklearn.metrics import f1_score, roc_auc_score, accuracy_score,precision_score,recall_score
accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred, average='macro')
recall = recall_score(y_test, y_pred, average='macro')
f1 = f1_score(y_test, y_pred, average='macro')
print(f'Accuracy: {accuracy}')
print(f'precision: {precision}')
print(f'Recall: {recall}')
print(f'F1 Score: {f1}')
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
import matplotlib.pyplot as plt
from sklearn.metrics import accuracy_score
from sklearn.metrics import f1_score


import seaborn as sn  #画图模块
from sklearn.metrics import confusion_matrix
def plot_matrix(y_true, y_pred, title_name):
    cm = confusion_matrix(y_true, y_pred)  # 混淆矩阵
    # annot = True 格上显示数字 ，fmt：显示数字的格式控制
    ax = sn.heatmap(cm, annot=True, fmt='g', xticklabels=['1', '2', '3'], yticklabels=['1', '2', '3'])
    # xticklabels、yticklabels指定横纵轴标签
    ax.set_title(title_name)  # 标题
    ax.set_xlabel('predict')  # x轴
    ax.set_ylabel('true')  # y轴
    plt.show()

# 调用函数画图
plot = plot_matrix(list(y_pred), list(y_test), 'example-confusion matrix')
# from sklearn.metrics import classification_report
# from sklearn.metrics import confusion_matrix
# import matplotlib.pyplot as plt
# from sklearn.metrics import accuracy_score
# from sklearn.metrics import f1_score
# import seaborn as sn  #画图模块
# from sklearn.metrics import confusion_matrix
# def plot_matrix(y_true, y_pred, title_name):
#     cm = confusion_matrix(y_true, y_pred)  # 混淆矩阵
#     # annot = True 格上显示数字 ，fmt：显示数字的格式控制
#     ax = sn.heatmap(cm, annot=True, fmt='g', xticklabels=['1', '2', '3'], yticklabels=['1', '2', '3'])
#     # xticklabels、yticklabels指定横纵轴标签
#     ax.set_title(title_name)  # 标题
#     ax.set_xlabel('predict')  # x轴
#     ax.set_ylabel('true')  # y轴
#     plt.show()
#
# # 调用函数画图
# plot = plot_matrix(list(y_pred), list(y_true), 'example-confusion matrix')