sanjianjixiang的博客

构建一个音乐推荐系统import pandas as pdimport numpy as npimport timeimport sqlite3data_home = 'F:/51学习/study/机器学习进阶/第14章Python从零开始构建音乐推荐系统/Python实现音乐推荐系统/'triplet_dataset = pd.read_csv(filepath_or_buffe...

饭店流量数据import pandas as pdair_visit = pd.read_csv('air_visit_data.csv')air_visit.index = pd.to_datetime(air_visit['visit_date'])air_visit.head()# 按天来算air_visit = air_visit.groupby('air_store_...

接上一篇<sklearn文本特征预处理1: WordPunctTokenizer, CountVectorizer, TF-IDF>五. Similarity特征# 余弦相似度from sklearn.metrics.pairwise import cosine_similaritysimilarity_matrix = cosine_similarity(tv_matrix...

构造一个文本数据集import pandas as pdimport numpy as npcorpus = ['The sky is blue and beautiful.', 'Love this blue and beautiful sky!', 'The quick brown fox jumps over the lazy dog.', ...

import pandas as pdimport numpy as npimport datetimefrom dateutil.parser import parse # parse根据字符串解析成datetime,字符串可以很随意,可用时间日期的英文单词,可用横线,逗号,空格等做分隔符import pytz # 时区time_stamps = ['2015-03-08 10:3...

import pandas as pdimport numpy as npfcc_survey_df = pd.read_csv('fcc_2016_coder_survey_subset.csv',encoding='utf-8')fcc_survey_df['Income_log'] = np.log(1 + fcc_survey_df['Income']) # 对数变换fcc_s...

import pandas as pdfcc_survey_df = pd.read_csv('fcc_2016_coder_survey_subset.csv',encoding='utf-8')fcc_survey_df[['ID.x','Age','Income']].iloc[2:7]import matplotlib.pyplot as pltimport matplotl...

import pandas as pdfcc_survey_df = pd.read_csv('fcc_2016_coder_survey_subset.csv',encoding='utf-8')fcc_survey_df[['ID.x','EmploymentField','Age','Income']].head()import matplotlib.pyplot as plt...

import pandas as pdpoke_df = pd.read_csv('Pokemon.csv', encoding='utf-8')atk_df = poke_df[['Attack', 'Defense']]atk_df.head()from sklearn.preprocessing import PolynomialFeaturespf = Polynomial...

import pandas as pdpopsong_df = pd.read_csv('song_views.csv',encoding='utf-8')popsong_df.head(10)首先直接用numpy实现二值化:import numpy as npwatched = np.array(popsong_df['listen_count'])watched[watch...

import pandas as pdpoke_df = pd.read_csv('Pokemon.csv', encoding='utf-8')poke_df[['Name','Generation']].iloc[4:10]gen_dummy_features = pd.get_dummies(poke_df['Generation'], drop_first=True) #去掉第...

import numpy as npimport pandas as pdpoke_df = pd.read_csv('Pokemon.csv', encoding='utf-8')poke_df[['Name', 'Generation', 'Legendary']].iloc[4:10]from sklearn.preprocessing import LabelEncoder...

import numpy as npimport pandas as pdpoke_df = pd.read_csv('Pokemon.csv', encoding='utf-8')poke_df.head(10)# 随机抽样poke_df = poke_df.sample(random_state=1, frac=1).reset_index(drop=True)# pandas...

import pandas as pdimport numpy as npvg_df = pd.read_csv('vgsales.csv', encoding = 'ISO-8859-1')vg_df[['Name', 'Platform', 'Year', 'Genre', 'Publisher']].iloc[1:7]genres = np.unique(vg_df['Genre...

数据预处理--标准化与归一化注意点:1: 标准化和归一化代码:2: plt.tight_layout()3: 如何在plot画图中输入数学符号????和????数据预处理实例对原始数据进行处理 , 有两种方法 :1: 标准化standardization ( 或者叫做Z-score normalization ) , 均值 ????=0 , 标准差 ????=1???? = (????−????) / ????2: 归一化M...