{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import pprint\n",
"import json"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'1.3.2'"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.__version__"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## create from lists"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" names | \n",
" ages | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" john | \n",
" 33 | \n",
"
\n",
" \n",
" 1 | \n",
" mary | \n",
" 22 | \n",
"
\n",
" \n",
" 2 | \n",
" peter | \n",
" 45 | \n",
"
\n",
" \n",
" 3 | \n",
" gary | \n",
" 23 | \n",
"
\n",
" \n",
" 4 | \n",
" anne | \n",
" 12 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" names ages\n",
"0 john 33\n",
"1 mary 22\n",
"2 peter 45\n",
"3 gary 23\n",
"4 anne 12"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"names = ['john','mary','peter','gary','anne']\n",
"ages = [33,22,45,23,12]\n",
"\n",
"df = pd.DataFrame({\n",
" 'names':names,\n",
" 'ages':ages\n",
"})\n",
"df"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## create from list of dicts"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" name | \n",
" gender | \n",
" age | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" john | \n",
" male | \n",
" 45 | \n",
"
\n",
" \n",
" 1 | \n",
" mary | \n",
" female | \n",
" 19 | \n",
"
\n",
" \n",
" 2 | \n",
" peter | \n",
" male | \n",
" 34 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" name gender age\n",
"0 john male 45\n",
"1 mary female 19\n",
"2 peter male 34"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_dicts = [\n",
" {'name':\"john\",\"gender\":'male','age':45},\n",
" {'name':\"mary\", 'gender':\"female\",'age':19},\n",
" {'name':\"peter\",'gender':'male', 'age':34}\n",
"]\n",
"\n",
"# must reassign since the append method does not work in place\n",
"df = pd.DataFrame.from_records(data_dicts)\n",
"df"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## create from single dict use keys as index"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{\n",
" \"alice\": 12,\n",
" \"bob\": 20,\n",
" \"charlie\": 33\n",
"}\n"
]
},
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" age | \n",
"
\n",
" \n",
" \n",
" \n",
" alice | \n",
" 12 | \n",
"
\n",
" \n",
" bob | \n",
" 20 | \n",
"
\n",
" \n",
" charlie | \n",
" 33 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" age\n",
"alice 12\n",
"bob 20\n",
"charlie 33"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"d = {\"alice\": 12, \"bob\": 20, \"charlie\": 33}\n",
"\n",
"print(json.dumps(d, indent=2))\n",
"\n",
"pd.DataFrame.from_dict(d, orient='index', columns=['age'])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## create an empty dataframe and append rows"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" col_a | \n",
" col_b | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 5.0 | \n",
" 10.0 | \n",
"
\n",
" \n",
" 1 | \n",
" 1.0 | \n",
" 100.0 | \n",
"
\n",
" \n",
" 2 | \n",
" 32.0 | \n",
" 999.0 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" col_a col_b\n",
"0 5.0 10.0\n",
"1 1.0 100.0\n",
"2 32.0 999.0"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.DataFrame()\n",
"\n",
"# must reassign since the append method does not work in place\n",
"df = df.append({'col_a':5,'col_b':10}, ignore_index=True)\n",
"df = df.append({'col_a':1,'col_b':100}, ignore_index=True)\n",
"df = df.append({'col_a':32,'col_b':999}, ignore_index=True)\n",
"\n",
"df"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": true
},
"source": [
"## crate dataframe with specific types"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" name | \n",
" gender | \n",
" age | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" john | \n",
" male | \n",
" 45 | \n",
"
\n",
" \n",
" 1 | \n",
" mary | \n",
" female | \n",
" 19 | \n",
"
\n",
" \n",
" 2 | \n",
" peter | \n",
" male | \n",
" 34 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" name gender age\n",
"0 john male 45\n",
"1 mary female 19\n",
"2 peter male 34"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_dicts = [\n",
" {'name':\"john\",\"gender\":'male','age':45},\n",
" {'name':\"mary\", 'gender':\"female\",'age':19},\n",
" {'name':\"peter\",'gender':'male', 'age':34}\n",
"]\n",
"\n",
"# must reassign since the append method does not work in place\n",
"df = pd.DataFrame.from_records(data_dicts,)\n",
"df"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.8.10"
},
"toc": {
"base_numbering": 1,
"nav_menu": {},
"number_sections": true,
"sideBar": true,
"skip_h1_title": false,
"title_cell": "Table of Contents",
"title_sidebar": "Contents",
"toc_cell": false,
"toc_position": {},
"toc_section_display": true,
"toc_window_display": false
}
},
"nbformat": 4,
"nbformat_minor": 2
}