From 1ad0207d51d32f8d7937abc4585c4598fdae1c56 Mon Sep 17 00:00:00 2001 From: wangchunlin Date: Sat, 15 Jul 2023 11:19:10 +0800 Subject: [PATCH] =?UTF-8?q?FeaturePr=5F3.py=E7=9B=B4=E6=8E=A5=E4=BB=8E?= =?UTF-8?q?=E6=BA=90=E6=96=87=E4=BB=B6=E8=AE=A1=E7=AE=97=EF=BC=8C=E4=B8=8D?= =?UTF-8?q?=E4=BB=8E=E4=B8=AD=E9=97=B4=E6=96=87=E4=BB=B6=E8=AE=A1=E7=AE=97?= =?UTF-8?q?=EF=BC=8C=E5=B7=B2=E7=BB=8F=E5=AF=B9=E6=AF=94=E8=BF=87=E4=BA=86?= =?UTF-8?q?=EF=BC=8C=E5=92=8C=E6=98=A8=E5=A4=A9FeaturePr=5F2.py=E6=98=AF?= =?UTF-8?q?=E4=B8=80=E6=A0=B7=E7=9A=84?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- Feature_Process_3.py | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 Feature_Process_3.py diff --git a/Feature_Process_3.py b/Feature_Process_3.py new file mode 100644 index 0000000..0c850e0 --- /dev/null +++ b/Feature_Process_3.py @@ -0,0 +1,37 @@ +import pandas as pd + +# 读取原始数据表 +df_src = pd.read_excel("data/data_src.xlsx") + +# 处理父亲教养方式数字化 +df_src['父亲教养方式数字化'] = df_src['父亲教养方式'].apply(lambda x: 0.59 if x == '温暖与理解' else 0.46) + +# 处理母亲教养方式数字化 +df_src['母亲教养方式数字化'] = df_src['母亲教养方式'].apply(lambda x: 0.69 if x == '温暖与理解' else 0.56) + +# 处理自评家庭经济条件数字化 +df_src['自评家庭经济条件数字化'] = df_src['自评家庭经济条件'].apply(lambda x: 0.54 if x in ['贫困', '较差'] else 0.47) + +# 处理有无心理治疗（咨询）史数字化 +df_src['有无心理治疗（咨询）史数字化'] = df_src['心理治疗（咨询）史'].apply(lambda x: 0.09 if x in ['无', '没有'] else 0.21) + +# 处理强迫症状数字化 +df_src['强迫症状数字化'] = df_src['强迫症状'] / 4 + +# 处理人际关系敏感症状数字化 +df_src['人际关系敏感症状数字化'] = df_src['人际关系敏感'] / 4 + +# 处理抑郁症状数字化 +df_src['抑郁症状数字化'] = df_src['抑郁'] / 4 + +# 计算多因子症状 +df_src['多因子症状'] = df_src[['躯体化', '强迫症状', '人际关系敏感', '抑郁', '焦虑', '敌对', '恐怖', '偏执', '精神病性', '其他']].apply(lambda row: sum(row > 3.0) / 10, axis=1) + +# 选择需要复制的列 +columns_to_copy = ['编号', '性别', '年龄', '父亲教养方式', '父亲教养方式数字化', '母亲教养方式', '母亲教养方式数字化', '自评家庭经济条件', '自评家庭经济条件数字化', '心理治疗（咨询）史', '有无心理治疗（咨询）史数字化', '躯体化', '强迫症状', '强迫症状数字化', '人际关系敏感', '人际关系敏感症状数字化', '抑郁', '抑郁症状数字化', '焦虑', '敌对', '恐怖', '偏执', '精神病性', '其他', '多因子症状'] + +# 复制选定的列到新表 +df_feature = df_src[columns_to_copy].copy() + +# 保存新表 +df_feature.to_excel("feature.xlsx", index=False)