python
python
金戈_旭日东升
这个作者很懒,什么都没留下…
展开
-
python array保存为csv文件,并加载
import numpy numpy.savetxt('train_x.csv', train_x, delimiter = ',')train_x.csv = numpy.loadtxt(open("train_x.csv","rb"),delimiter=",",skiprows=0)原创 2021-11-25 10:18:04 · 8398 阅读 · 0 评论 -
keras ANN 分类实战
import pandas as pdimport numpy as npfrom sklearn.model_selection import train_test_splitfrom keras.utils import np_utils## 数据准备# 读入数据文件# pandas库的读取文件,header指明引入的文档是没有的列的,自动编号data=pd.read_csv('iris.txt',header=None,sep=' ').valuesdata=data[:,1:6]原创 2021-11-23 11:13:07 · 5319 阅读 · 0 评论 -
ANN 回归预测实战
import pandas as pd # 数据科学计算工具import numpy as np # 数值计算工具from sklearn.metrics import mean_squared_errorfrom sklearn.metrics import r2_scorefrom sklearn.metrics import mean_absolute_error # 平方绝对误差from math import sqrttrain_path = r'WWT_data.csv'dat原创 2021-11-15 11:48:07 · 2907 阅读 · 0 评论 -
xgboost 序列数据实战
import pandas as pdimport matplotlib.pyplot as pltimport numpy as npimport xgboost as xgbfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import mean_absolute_percentage_errorfrom sklearn.model_selection import GridSearchCVfr原创 2021-11-04 18:54:01 · 222 阅读 · 0 评论 -
2021-10-24 画图
import matplotlib.pyplot as pltimport pandas as pdimport numpy as npfrom sklearn.metrics import mean_squared_errorfrom sklearn.metrics import r2_scorefrom sklearn.metrics import mean_absolute_error # 平方绝对误差from math import sqrtimport matplotlib as m原创 2021-10-24 11:16:12 · 84 阅读 · 0 评论 -
决策树分裂可视化
# -*- coding: utf-8 -*-"""Created on Mon Aug 16 10:43:40 2021@author: 1"""import dtreevizimport pandas as pdimport numpy as npfrom sklearn.datasets import *from sklearn import tree'''iris = load_iris()df_iris = pd.DataFrame(iris['data'],column原创 2021-08-18 13:57:26 · 149 阅读 · 0 评论 -
catboost 分类实战
# -*- coding: utf-8 -*-"""Created on Fri Aug 6 15:23:19 2021@author: 1"""import pandas as pdfrom catboost import CatBoostClassifierimport pandas as pdfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import f1_scorefrom原创 2021-08-18 13:48:29 · 2531 阅读 · 0 评论 -
lightGBM 分类实战
import pandas as pdimport numpy as npimport osimport warningsfrom sklearn.metrics import f1_score,accuracy_scorefrom sklearn.model_selection import StratifiedKFold, KFoldfrom tqdm import tqdmimport lightgbmfrom sklearn.feature_extraction.text impor原创 2021-08-18 13:46:23 · 443 阅读 · 0 评论 -
python读取数据库特定值
import pymysqlimport pandas as pdconn = pymysql.connect( host="localhost", user="root",password="123456", database="spring-data", charset="utf8")#提取进水DOSAcursor = conn.cursor()sql = "SELECT PV FROM honghe WHERE TagName = 'DOSA'"curso原创 2021-07-26 14:12:43 · 684 阅读 · 0 评论 -
python dataframe类型数据index重置从零开始
result=result.reset_index(drop=True)原创 2021-07-25 20:35:32 · 2218 阅读 · 0 评论 -
python 散点图加趋势线
import numpy as npimport pylabx=[1,2,3,4,5]y=[2,3,5,7,9]pylab.plot(x,y,'o') z = np.polyfit(x, y, 1) p = np.poly1d(z) pylab.plot(x,p(x),"r")原创 2021-07-05 14:27:13 · 6802 阅读 · 0 评论 -
TF—IDF
sklearn文本特征提取——TfidfVectorizer 什么是TF-IDFTF-IDF(term frequency-inverse document frequency)词频-逆向文件频率。在处理文本时,如何将文字转化为模型可以处理的向量呢?TF-IDF就是这个问题的解决方案之一。字词的重要性与其在文本中出现的频率成正比(TF),与其在语料库中出现的频率成反比(IDF)。TFTF:词频。TF(w)=(词w在文档中...原创 2020-07-13 13:54:49 · 122 阅读 · 0 评论 -
python 三维数组保存并读取
#保存data.tofile("filename.bin")#读取A=np.fromfile("filename.bin")#转换aaa=np.reshape(A,(a,b,c))#a,b,c为第一,二,三维原创 2020-06-23 14:03:24 · 8251 阅读 · 0 评论 -
python 三维数组合并拼接
dd=np.vstack((d,ccc))一、连接数组import numpy as npa = np.arange(3)b = np.arange(10,13)print(a)print(b)12345[0 1 2][10 11 12]121.最基本的函数:concatenatenp.concatenate((a,b)) # 默认axis=01array([ 0, 1, 2, 10, 11, 12])12.vstack:垂直连接数组(axis=...原创 2020-06-23 11:16:57 · 12791 阅读 · 1 评论 -
python SQL语句变量拼接
tablename = ['t_acq_data_20180901','t_acq_data_20180902']curtable=tablename[0]sql = "SELECT SHIP_ID,LONGITUDE,LATITUDE,SPEED,TACK,CREATE_TIME From " +curtable + " WHERE SHIP_ID='35512'"cursor.execute(sql)results = cursor.fetchall()原创 2020-06-11 15:44:50 · 3970 阅读 · 0 评论 -
LGB 模型保存及应用
1 原生模式# 模型训练gbm = lgb.train(params, lgb_train, num_boost_round=20, valid_sets=lgb_eval, early_stopping_rounds=5) # 模型保存gbm.save_model('model.txt') # 模型加载gbm = lgb.Booster(model_file='model.txt') # 模型预测y_pred = gbm.predict(X_test, num_iteration=.原创 2020-06-09 15:45:26 · 6067 阅读 · 0 评论 -
Python 求每行的概率最大值()
a=np.argmax(b,axis=1)原创 2020-06-09 15:38:15 · 665 阅读 · 0 评论 -
Python 读取多个CSV文件整合到一个CSV文件
def get_data(path): df_list = [] for file in tqdm(os.listdir(path)):##进度条 file_path = os.path.join(path, file) df = pd.read_csv(file_path) df_list.append(df) df = pd.concat(df_list) return dfTEST_PATH = './data/hy...原创 2020-06-02 13:36:36 · 6612 阅读 · 2 评论 -
python 链接本地MySQL数据库
import MySQLdbdb = MySQLdb.connect("localhost", "root", "123456", "app", charset='utf8' )cursor = db.cursor()sql = "SELECT * FROM userInfo WHERE userName ='xsf' "cursor.execute(sql)results = cursor.fetchall()print(results)runfile('C:/Users/1/Desk.原创 2020-05-28 19:34:17 · 1253 阅读 · 0 评论