Files
2025-10-20 12:32:18 +08:00

332 lines
7.4 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 25,
"id": "d99d999d",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "955684bc",
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_excel(\"./学生信息.xls\", usecols=['学号', '姓名', '性别', '年级','班级'])"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "7a49db1c",
"metadata": {},
"outputs": [],
"source": [
"class_count = df.groupby(['年级', '班级']).size().reset_index(name='人数')"
]
},
{
"cell_type": "code",
"execution_count": 29,
"id": "3e00f787",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>年级</th>\n",
" <th>班级</th>\n",
" <th>人数</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>26学部</td>\n",
" <td>1班</td>\n",
" <td>42</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>26学部</td>\n",
" <td>2班</td>\n",
" <td>41</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>26学部</td>\n",
" <td>3班</td>\n",
" <td>38</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>26学部</td>\n",
" <td>4班</td>\n",
" <td>40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>26学部</td>\n",
" <td>5班</td>\n",
" <td>39</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>27学部</td>\n",
" <td>1班</td>\n",
" <td>48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>27学部</td>\n",
" <td>2班</td>\n",
" <td>47</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>27学部</td>\n",
" <td>3班</td>\n",
" <td>46</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>27学部</td>\n",
" <td>4班</td>\n",
" <td>48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>27学部</td>\n",
" <td>5班</td>\n",
" <td>48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>28学部</td>\n",
" <td>1班</td>\n",
" <td>49</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>28学部</td>\n",
" <td>2班</td>\n",
" <td>49</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>28学部</td>\n",
" <td>3班</td>\n",
" <td>49</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>28学部</td>\n",
" <td>4班</td>\n",
" <td>49</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 年级 班级 人数\n",
"0 26学部 1班 42\n",
"1 26学部 2班 41\n",
"2 26学部 3班 38\n",
"3 26学部 4班 40\n",
"4 26学部 5班 39\n",
"5 27学部 1班 48\n",
"6 27学部 2班 47\n",
"7 27学部 3班 46\n",
"8 27学部 4班 48\n",
"9 27学部 5班 48\n",
"10 28学部 1班 49\n",
"11 28学部 2班 49\n",
"12 28学部 3班 49\n",
"13 28学部 4班 49"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"class_count"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bc5324c0",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 13,
"id": "6a622610",
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_excel(\"./学生信息.xls\", usecols=['学号', '姓名', '性别', '年级'])\n",
"row_strings = set()\n",
"for _, row in df.iterrows():\n",
" row_str = f\"{row['学号']}{row['姓名']}{row['性别']}{row['年级']}\"\n",
" row_strings.add(row_str)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "c2b0ab79",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(633, 4)"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.shape"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "e5f90213",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"633"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(row_strings)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "0ec9fe0a",
"metadata": {},
"outputs": [],
"source": [
"df1 = pd.read_excel(\"./学生信息2.xls\", usecols=['学号', '姓名', '性别', '年级'])\n",
"row_strings1 = set()\n",
"for _, row in df.iterrows():\n",
" row_str = f\"{row['学号']}{row['姓名']}{row['性别']}{row['年级']}\"\n",
" row_strings1.add(row_str)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "75d2483a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'260434于铭达男26学部'"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"row_strings1.pop()"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "e5180f79",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'260434于铭达男26学部'}"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"row_strings - row_strings1 "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e87426b4",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"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": "3.12.4"
}
},
"nbformat": 4,
"nbformat_minor": 5
}