91av视频/亚洲h视频/操亚洲美女/外国一级黄色毛片 - 国产三级三级三级三级

資源簡介

本資源是基于python實現的Boston Housing 數據集房價預測回歸問題,調用了sklearn中5種回歸算法對房價進行預測。

資源截圖

代碼片段和文件信息

#?-*-?coding:?utf-8?-*-
“““
Created?on?Wed?Dec?12?20:51:03?2018

@author:?28770
“““

#導入所需的函數模塊
import?numpy?as?np?
import?pandas?as?pd?

import?seaborn?as?sns
from?matplotlib?import?pyplot?as?plt
sns.set(style=“whitegrid“)

import?warnings
warnings.filterwarnings(“ignore“)
warnings.filterwarnings(“ignore“?category=DeprecationWarning)?

#載入原始數據
training?=?pd.read_csv(“C:\\Users\\28770\\DISKE\\working?code\\train.csv“)
testing?=?pd.read_csv(“C:\\Users\\28770\\DISKE\\working?code\\test.csv“)

#觀察原始數據分布方式及其各屬性相關性
training.head()
training.describe()
training.shape
training.keys()

correlations?=?training.corr()
correlations?=?correlations[“SalePrice“].sort_values(ascending=False)
features?=?correlations.index[1:6]
correlations

#檢驗訓練集及測試集中的缺失項數據
training_null?=?pd.isnull(training).sum()
testing_null?=?pd.isnull(testing).sum()
null?=?pd.concat([training_null?testing_null]?axis=1?keys=[“Training“?“Testing“])

null_many?=?null[null.sum(axis=1)?>?200]??#包含大量缺失項元素的屬性
null_few?=?null[(null.sum(axis=1)?>?0)?&?(null.sum(axis=1)?null_many

#NaN代表特定含義的屬性集合
null_has_meaning?=?[“Alley“?“BsmtQual“?“BsmtCond“?“BsmtExposure“?“BsmtFinType1“?“BsmtFinType2“?“FireplaceQu“?“GarageType“?“GarageFinish“?“GarageQual“?“GarageCond“?“PoolQC“?“Fence“?“MiscFeature“]
for?i?in?null_has_meaning:
????training[i].fillna(“None“?inplace=True)
????testing[i].fillna(“None“?inplace=True)
????
#按照中值填充數值屬性的缺失項
from?sklearn.preprocessing?import?Imputer
imputer?=?Imputer(strategy=“median“)

#再次檢驗訓練集及測試集中的缺失項數據
training_null?=?pd.isnull(training).sum()
testing_null?=?pd.isnull(testing).sum()
null?=?pd.concat([training_null?testing_null]?axis=1?keys=[“Training“?“Testing“])

null_many?=?null[null.sum(axis=1)?>?200]??#包含大量缺失項元素的屬性
null_few?=?null[(null.sum(axis=1)?>?0)?&?(null.sum(axis=1)?null_many

#舍棄掉包含較多缺失項的屬性“LotFrontage“
training.drop(“LotFrontage“?axis=1?inplace=True)
testing.drop(“LotFrontage“?axis=1?inplace=True)

#對其余包含較多缺失項的屬性進行相應的元素填充
null_few
training[“GarageYrBlt“].fillna(training[“GarageYrBlt“].median()?inplace=True)
testing[“GarageYrBlt“].fillna(testing[“GarageYrBlt“].median()?inplace=True)
training[“MasVnrArea“].fillna(training[“MasVnrArea“].median()?inplace=True)
testing[“MasVnrArea“].fillna(testing[“MasVnrArea“].median()?inplace=True)
training[“MasVnrType“].fillna(“None“?inplace=True)
testing[“MasVnrType“].fillna(“None“?inplace=True)

#區分訓練集中的數值屬性和類別屬性
types_train?=?training.dtypes?#屬性的數據類型包括:?int?float?object
num_train?=?types_train[(types_train?==?int)?|?(types_train?==?float)]?#數值屬性類型包括?int?or?float
cat_train?=?types_train[types_train?==?object]?#類別屬性類型包括?object

#對訓練集進行相同的處理
types_test?=?testing.dtypes
num_test?=?types_test[(types_test?==?int)?|?(types_test?==?float)]
cat_test?=?types_test[types_test?==?object]

#將?num_train?和?num_test?轉變為較易處理的列表形式
numerical_values_train?=?list(num_train.index)
numerical_val

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----

?????文件??????13719??2018-12-12?21:17??house-prices-predicting\house-prices-predicting.py

?????文件??????31939??2018-12-10?21:43??house-prices-predicting\sample_submission.csv

?????文件?????451405??2018-12-10?21:43??house-prices-predicting\test.csv

?????文件?????460676??2018-12-10?21:43??house-prices-predicting\train.csv

?????文件????????102??2018-12-14?11:07??house-prices-predicting\文檔說明.txt

?????目錄??????????0??2018-12-14?11:06??house-prices-predicting

-----------?---------??----------?-----??----

???????????????957841????????????????????6


評論

共有 條評論