{
“cells”: [
{
“cell_type”: “markdown”,
“metadata”: {},
“source”: [
“# 导入数据”
]
},
{
“cell_type”: “code”,
“execution_count”: 27,
“metadata”: {},
“outputs”: [
{
“data”: {
“text/html”: [
“

  "text/plain": [
   "  Patient_name Label   Date  \\\n",
   "0    患者：女  43岁    压抑  05.28   \n",
   "\n",
   "                                               Title  Communications Doctor  \\\n",
   "0  压抑 个人情况：去年1月份开始夫妻两地分居，孩子13岁男孩住校，平... 这种情况是否需要去...             115    杨胜文   \n",
   "\n",
   "  Hospital Faculty  \n",
   "0  襄阳市安定医院     心理科  "
  ]
 },
 "execution_count": 27,
 "metadata": {},
 "output_type": "execute_result"
}

],
“source”: [
“import pandas as pd\n”,
“from pyecharts.charts import \n",
“from pyecharts import options as opts\n”,
“\n”,
“df=pd.read_csv(‘YiYuZheng.csv’)\n”,
“df.head(1)”
]
},
{
“cell_type”: “code”,
“execution_count”: 28,
“metadata”: {},
“outputs”: [
{
“name”: “stdout”,
“output_type”: “stream”,
“text”: [
“<class ‘pandas.core.frame.DataFrame’>\n”,
“RangeIndex: 8400 entries, 0 to 8399\n”,
“Data columns (total 8 columns):\n”,
" # Column Non-Null Count Dtype \n",
“— ------ -------------- ----- \n”,
" 0 Patient_name 8400 non-null object\n",
" 1 Label 8400 non-null object\n",
" 2 Date 8288 non-null object\n",
" 3 Title 8400 non-null object\n",
" 4 Communications 8400 non-null int64 \n",
" 5 Doctor 8400 non-null object\n",
" 6 Hospital 8400 non-null object\n",
" 7 Faculty 8400 non-null object\n",
“dtypes: int64(1), object(7)\n”,
“memory usage: 525.1+ KB\n”
]
}
],
“source”: [
"# 查看数据\n",*
“df.info()”
]
},
{
“cell_type”: “markdown”,
“metadata”: {},
“source”: [
“从数据反馈结果来看：Date列存在空缺值，并且不是日期类型。\n”,
“\n”,
“Patient_name列存在信息混合一起情况，需要拆分年龄和性别。”
]
},
{
“cell_type”: “markdown”,
“metadata”: {},
“source”: [
“# 数据预处理”
]
},
{
“cell_type”: “markdown”,
“metadata”: {},
“source”: [
“## 拆分年龄和性别”
]
},
{
“cell_type”: “code”,
“execution_count”: 29,
“metadata”: {},
“outputs”: [
{
“data”: {
“text/html”: [
“

  "text/plain": [
   "  Patient_name           Label   Date  \\\n",
   "0    患者：女  43岁              压抑  05.28   \n",
   "1    患者：女  32岁        生气。心梗。抑郁  05.28   \n",
   "2    患者：女  15岁       情绪低落，烦躁抑郁  05.28   \n",
   "3    患者：女  16岁              抑郁  05.28   \n",
   "4    患者：女  67岁  焦虑症 严重躯干反应、抑郁症  05.28   \n",
   "\n",
   "                                               Title  Communications Doctor  \\\n",
   "0  压抑 个人情况：去年1月份开始夫妻两地分居，孩子13岁男孩住校，平... 这种情况是否需要去...             115    杨胜文   \n",
   "1      生气。心梗。抑郁 郁郁寡欢。被他人语言刺激。卧床不起。没动力。心疼。受伤 是什么病。怎么办              12    郭汉法   \n",
   "2  情绪低落，烦躁抑郁 情绪低落，压抑烦躁，思考能力降低。长时间学习，睡眠时间少。睡... 还有...               2    郭苏皖   \n",
   "3  抑郁 前面已简述，2024年夏季中考，本来学习非常好，非常自律，自... 已经服用9个月的艾...               2     刘丽   \n",
   "4  焦虑症 严重躯干反应   抑郁症 草酸加量以后，还是有比较严重的躯干反应，主要表现为背痛 脖...               2    刘晓华   \n",
   "\n",
   "             Hospital      Faculty Sex Age  \n",
   "0             襄阳市安定医院          心理科   女  43  \n",
   "1             泰安八十八医院        临床心理科   女  32  \n",
   "2              南京脑科医院        医学心理科   女  15  \n",
   "3  联勤保障部队第九〇四医院（常州院区）  精神3科（物质依赖科）   女  16  \n",
   "4           上海市精神卫生中心          精神科   女  67  "
  ]
 },
 "execution_count": 29,
 "metadata": {},
 "output_type": "execute_result"
}

],
“source”: [
“#获取性别，作为新列\n”,
“#患者：女 43岁,首先按照空格拆分，结果为[患者：女]\[ ]\[43岁],选取第一个，第二次按照中文冒号拆分，[患者][: ][女]\n”,
“df[‘Sex’]=df[‘Patient_name’].map(lambda x:x.split(” “)[0]).map(lambda x:x.split(”：“)[-1])\n”,
“\n”,
“#获取年龄，作为新列\n”,
“#患者：女 43岁,首先按照空格拆分，结果为[患者：女]\[ ]\[43岁],选取第三个，并且去掉“岁”\n”,
“df[‘Age’]=df[‘Patient_name’].map(lambda x:x.split(” “)[2][:-1])\n”,
“\n”,
“df.head()”
]
},
{
“cell_type”: “markdown”,
“metadata”: {},
“source”: [
“## 处理空缺值”
]

},
{
“cell_type”: “code”,
“execution_count”: 30,
“metadata”: {},
“outputs”: [
{
“data”: {
“text/plain”: [
“Patient_name 0\n”,
“Label 0\n”,
“Date 112\n”,
“Title 0\n”,
“Communications 0\n”,
“Doctor 0\n”,
“Hospital 0\n”,
“Faculty 0\n”,
“Sex 0\n”,
“Age 0\n”,
“dtype: int64”
]
},
“execution_count”: 30,
“metadata”: {},
“output_type”: “execute_result”
}
],
“source”: [
“df.isnull().sum()”
]
},
{
“cell_type”: “code”,
“execution_count”: 31,
“metadata”: {},
“outputs”: [],
“source”: [
“#因为空缺数据较少，并且不适合使用填充法，故而删除\n”,
“df.dropna(inplace=True)#在原来的数据上删除”
]

},
{
“cell_type”: “code”,
“execution_count”: 32,
“metadata”: {},
“outputs”: [
{
“name”: “stdout”,
“output_type”: “stream”,
“text”: [
“<class ‘pandas.core.frame.DataFrame’>\n”,
“Int64Index: 8288 entries, 0 to 8399\n”,
“Data columns (total 10 columns):\n”,
" # Column Non-Null Count Dtype \n",
“— ------ -------------- ----- \n”,
" 0 Patient_name 8288 non-null object\n",
" 1 Label 8288 non-null object\n",
" 2 Date 8288 non-null object\n",
" 3 Title 8288 non-null object\n",
" 4 Communications 8288 non-null int64 \n",
" 5 Doctor 8288 non-null object\n",
" 6 Hospital 8288 non-null object\n",
" 7 Faculty 8288 non-null object\n",
" 8 Sex 8288 non-null object\n",
" 9 Age 8288 non-null object\n",
“dtypes: int64(1), object(9)\n”,
“memory usage: 712.2+ KB\n”
]
}
],
“source”: [
“df.info()”
]
},
{
“cell_type”: “markdown”,
“metadata”: {},
“source”: [
“## 修改Date列”
]
},
{
“cell_type”: “code”,
“execution_count”: 33,
“metadata”: {},
“outputs”: [],
“source”: [
“#df[‘Date’]\n”,
“#转换成字符串类型\n”,
“df[‘Date’]=df[‘Date’].astype(str)\n”,
“\n”,
“#定义函数，实现date列格式统一：年-月-日\n”,
“def trans_date(tag):\n”,
" if tag.startswith(“20”):#查看是否以20开头，即查看是否存在年\n",
" tag=tag.replace(“.”,“-”)\n",
" else:\n",
" tag=“2025-”+tag.replace(“.”,“-”)#否则加上年份\n",
" return tag\n",
“\n”,
“df[‘Date’]= df[‘Date’].map(lambda x:trans_date(x))#调用函数转换格式\n”,
“\n”,
“#转换成日期类型\n”,
“df[‘Date’]=pd.to_datetime(df[‘Date’])\n”,
“\n”,
“#df.info()”
]
},
{
“cell_type”: “markdown”,
“metadata”: {},
“source”: [
“# 数据可视化分析”
]
},
{
“cell_type”: “code”,
“execution_count”: 19,
“metadata”: {},
“outputs”: [],
“source”: [
“from pyecharts.globals import ThemeType #导入主题库”
]
},
{
“cell_type”: “markdown”,
“metadata”: {},
“source”: [
“## 查看患者性别分布情况”
]
},
{
“cell_type”: “code”,
“execution_count”: 41,
“metadata”: {},
“outputs”: [
{
“data”: {
“text/html”: [
“\n”,
“\n"
],
“text/plain”: [
“<pyecharts.render.display.HTML at 0x18dbfdb6100>”
]
},
“execution_count”: 41,
“metadata”: {},
“output_type”: “execute_result”
}
],
“source”: [
“#准备数据：按照性别统计个数\n”,
“data=df[‘Sex’].value_counts()\n”,
“#data\n”,
“x=data.index.tolist()\n”,
“y=data.tolist()\n”,
“\n”,
“#绘制饼图\n”,

"pie=(\n",
"    Pie(init_opts=opts.InitOpts(theme=ThemeType.LIGHT))#设置主题\n",
"    .add(\"\",\n",
"         [list(z) for z in zip(x,y)],#数据需要打包成[(key,value),(key,value),...]\n",
"         label_opts=opts.LabelOpts(formatter=\"{b}:{d}%\")#以百分比形式显示标签\n",
"        )\n",
"    .set_global_opts(title_opts=opts.TitleOpts(title=\"患者性别分布情况\"))\n",
")\n",
"pie.render_notebook()"

]
},
{
“cell_type”: “markdown”,
“metadata”: {},
“source”: [
“## 患者年龄分布情况”
]
},
{
“cell_type”: “code”,
“execution_count”: 34,
“metadata”: {},
“outputs”: [],
“source”: [
“#数据准备\n”,
“#1.转换年龄为数值类型\n”,
“#df[‘Age’]=df[‘Age’].astype(int)\n”,
“#因为年龄数据不规范，存在：X岁Y月 形式的数据，再次进行数据处理\n”,
“df[‘Age’]=df[‘Age’].map(lambda x:“1” if (“天” in x or “个” in x or “月” in x) else x).astype(int)\n”,
“#df.info()”
]
},
{
“cell_type”: “code”,
“execution_count”: 40,
“metadata”: {},
“outputs”: [
{
“data”: {
“text/html”: [
“\n”,
“\n"
],
“text/plain”: [
“<pyecharts.render.display.HTML at 0x1f3c6256940>”
]
},
“execution_count”: 6,
“metadata”: {},
“output_type”: “execute_result”
}
],
“source”: [
“data=df[‘Faculty’].value_counts()[:10] #选取前十科室\n”,
“\n”,
“pie=(\n”,
" Pie()\n",
" .add(‘’,[list(z) for z in zip(data.index.tolist(),data.tolist())],#饼图数据格式[[key1,value1],[key2,value2],…]\n",
" label_opts=opts.LabelOpts(formatter=“{b}:{d}%”)#标签格式\n",
" )\n",
“)\n”,
“pie.render_notebook()”
]
},
{
“cell_type”: “code”,
“execution_count”: null,
“metadata”: {},
“outputs”: [],
“source”: []
}
],
“metadata”: {
“kernelspec”: {
“display_name”: “Python 3”,
“language”: “python”,
“name”: “python3”
},
“language_info”: {
“codemirror_mode”: {
“name”: “ipython”,
“version”: 3
},
“file_extension”: “.py”,
“mimetype”: “text/x-python”,
“name”: “python”,
“nbconvert_exporter”: “python”,
“pygments_lexer”: “ipython3”,
“version”: “3.8.5”
}
},
“nbformat”: 4,
“nbformat_minor”: 4
}
![

## 在这里插入图片描述

*](https://i-blog.csdnimg.cn/direct/f3381692840e4ae2872e741d34349439.png#pic_center