From 5a1bae3e5b8f63c8b0fe3e77bcaaccb88b253752 Mon Sep 17 00:00:00 2001
From: pagqhcmx2 <3410248804@qq.com>
Date: Mon, 27 May 2024 14:31:38 +0800
Subject: [PATCH] =?UTF-8?q?=E6=B8=85=E6=B4=97=E7=88=AC=E5=8F=96=E6=95=B0?=
 =?UTF-8?q?=E6=8D=AE?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 new_house_clean.py | 43 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)
 create mode 100644 new_house_clean.py

diff --git a/new_house_clean.py b/new_house_clean.py
new file mode 100644
index 0000000..dfb46d0
--- /dev/null
+++ b/new_house_clean.py
@@ -0,0 +1,43 @@
+'''清洗房天下新房数据'''
+import os
+import pandas as pd
+# 读取数据
+df1 = pd.read_excel(r'./房天下新房数据.xlsx', index_col=0)
+# 清洗行政区\t\n
+df1['行政区'] = df1['行政区'].str.replace('\t', '').str.replace('\n', '')
+
+# 处理户型字段
+df2 = df1.dropna(subset=['户型'])
+# 索引：户型list
+hxdict = dict(df2['户型'].str.split('/'))
+for i, vlist in hxdict.items():
+    for v in vlist:
+        df1.loc[i, v] = '有'
+col_list = df1.columns.tolist()[5:]
+for col in col_list:
+    df1.loc[df1[col].isna(), col] = '无'
+# 处理面积字段
+df3 = df1.dropna(subset=['面积'])
+# 索引：面积list
+mjlist = dict(df3['面积'].str.split('~'))
+for i, vlist in mjlist.items():
+    # 只有一个数据，最大最小面积一样
+    if len(vlist) == 1:
+        df1.loc[i, '最小面积(㎡)'] = vlist[0]
+        df1.loc[i, '最大面积(㎡)'] = vlist[0]
+    else:
+        df1.loc[i, '最小面积(㎡)'] = vlist[0]
+        df1.loc[i, '最大面积(㎡)'] = vlist[1]
+
+
+# 重排columns顺序
+df4 = df1.loc[:, ['名称', '一居', '二居', '三居', '四居', '五居', '五居以上', '最小面积(㎡)', '最大面积(㎡)', '行政区', '价格(元/㎡)']]
+# 清除存在空值的行
+df4=df4.dropna()
+# 重排索引
+df4= df4.reset_index(drop=True)
+
+# # 存入清洗后的数据
+df4.to_excel(r'./房天下新房数据（清洗后）.xlsx')
+# 打开文件
+os.startfile(r"房天下新房数据（清洗后）.xlsx")
\ No newline at end of file