diff options
Diffstat (limited to 'docs/sqlglot/dataframe.html')
| -rw-r--r-- | docs/sqlglot/dataframe.html | 506 |
1 files changed, 506 insertions, 0 deletions
diff --git a/docs/sqlglot/dataframe.html b/docs/sqlglot/dataframe.html new file mode 100644 index 0000000..ea6f345 --- /dev/null +++ b/docs/sqlglot/dataframe.html @@ -0,0 +1,506 @@ +<!doctype html> +<html lang="en"> +<head> + <meta charset="utf-8"> + <meta name="viewport" content="width=device-width, initial-scale=1"> + <meta name="generator" content="pdoc 12.3.1"/> + <title>sqlglot.dataframe API documentation</title> + + <style>/*! * Bootstrap Reboot v5.0.0 (https://getbootstrap.com/) * Copyright 2011-2021 The Bootstrap Authors * Copyright 2011-2021 Twitter, Inc. * Licensed under MIT (https://github.com/twbs/bootstrap/blob/main/LICENSE) * Forked from Normalize.css, licensed MIT (https://github.com/necolas/normalize.css/blob/master/LICENSE.md) */*,::after,::before{box-sizing:border-box}@media (prefers-reduced-motion:no-preference){:root{scroll-behavior:smooth}}body{margin:0;font-family:system-ui,-apple-system,"Segoe UI",Roboto,"Helvetica Neue",Arial,"Noto Sans","Liberation Sans",sans-serif,"Apple Color Emoji","Segoe UI Emoji","Segoe UI Symbol","Noto Color Emoji";font-size:1rem;font-weight:400;line-height:1.5;color:#212529;background-color:#fff;-webkit-text-size-adjust:100%;-webkit-tap-highlight-color:transparent}hr{margin:1rem 0;color:inherit;background-color:currentColor;border:0;opacity:.25}hr:not([size]){height:1px}h1,h2,h3,h4,h5,h6{margin-top:0;margin-bottom:.5rem;font-weight:500;line-height:1.2}h1{font-size:calc(1.375rem + 1.5vw)}@media (min-width:1200px){h1{font-size:2.5rem}}h2{font-size:calc(1.325rem + .9vw)}@media (min-width:1200px){h2{font-size:2rem}}h3{font-size:calc(1.3rem + .6vw)}@media (min-width:1200px){h3{font-size:1.75rem}}h4{font-size:calc(1.275rem + .3vw)}@media (min-width:1200px){h4{font-size:1.5rem}}h5{font-size:1.25rem}h6{font-size:1rem}p{margin-top:0;margin-bottom:1rem}abbr[data-bs-original-title],abbr[title]{-webkit-text-decoration:underline dotted;text-decoration:underline dotted;cursor:help;-webkit-text-decoration-skip-ink:none;text-decoration-skip-ink:none}address{margin-bottom:1rem;font-style:normal;line-height:inherit}ol,ul{padding-left:2rem}dl,ol,ul{margin-top:0;margin-bottom:1rem}ol ol,ol ul,ul ol,ul ul{margin-bottom:0}dt{font-weight:700}dd{margin-bottom:.5rem;margin-left:0}blockquote{margin:0 0 1rem}b,strong{font-weight:bolder}small{font-size:.875em}mark{padding:.2em;background-color:#fcf8e3}sub,sup{position:relative;font-size:.75em;line-height:0;vertical-align:baseline}sub{bottom:-.25em}sup{top:-.5em}a{color:#0d6efd;text-decoration:underline}a:hover{color:#0a58ca}a:not([href]):not([class]),a:not([href]):not([class]):hover{color:inherit;text-decoration:none}code,kbd,pre,samp{font-family:SFMono-Regular,Menlo,Monaco,Consolas,"Liberation Mono","Courier New",monospace;font-size:1em;direction:ltr;unicode-bidi:bidi-override}pre{display:block;margin-top:0;margin-bottom:1rem;overflow:auto;font-size:.875em}pre code{font-size:inherit;color:inherit;word-break:normal}code{font-size:.875em;color:#d63384;word-wrap:break-word}a>code{color:inherit}kbd{padding:.2rem .4rem;font-size:.875em;color:#fff;background-color:#212529;border-radius:.2rem}kbd kbd{padding:0;font-size:1em;font-weight:700}figure{margin:0 0 1rem}img,svg{vertical-align:middle}table{caption-side:bottom;border-collapse:collapse}caption{padding-top:.5rem;padding-bottom:.5rem;color:#6c757d;text-align:left}th{text-align:inherit;text-align:-webkit-match-parent}tbody,td,tfoot,th,thead,tr{border-color:inherit;border-style:solid;border-width:0}label{display:inline-block}button{border-radius:0}button:focus:not(:focus-visible){outline:0}button,input,optgroup,select,textarea{margin:0;font-family:inherit;font-size:inherit;line-height:inherit}button,select{text-transform:none}[role=button]{cursor:pointer}select{word-wrap:normal}select:disabled{opacity:1}[list]::-webkit-calendar-picker-indicator{display:none}[type=button],[type=reset],[type=submit],button{-webkit-appearance:button}[type=button]:not(:disabled),[type=reset]:not(:disabled),[type=submit]:not(:disabled),button:not(:disabled){cursor:pointer}::-moz-focus-inner{padding:0;border-style:none}textarea{resize:vertical}fieldset{min-width:0;padding:0;margin:0;border:0}legend{float:left;width:100%;padding:0;margin-bottom:.5rem;font-size:calc(1.275rem + .3vw);line-height:inherit}@media (min-width:1200px){legend{font-size:1.5rem}}legend+*{clear:left}::-webkit-datetime-edit-day-field,::-webkit-datetime-edit-fields-wrapper,::-webkit-datetime-edit-hour-field,::-webkit-datetime-edit-minute,::-webkit-datetime-edit-month-field,::-webkit-datetime-edit-text,::-webkit-datetime-edit-year-field{padding:0}::-webkit-inner-spin-button{height:auto}[type=search]{outline-offset:-2px;-webkit-appearance:textfield}::-webkit-search-decoration{-webkit-appearance:none}::-webkit-color-swatch-wrapper{padding:0}::file-selector-button{font:inherit}::-webkit-file-upload-button{font:inherit;-webkit-appearance:button}output{display:inline-block}iframe{border:0}summary{display:list-item;cursor:pointer}progress{vertical-align:baseline}[hidden]{display:none!important}</style> + <style>/*! syntax-highlighting.css */pre{line-height:125%;}span.linenos{color:inherit; background-color:transparent; padding-left:5px; padding-right:20px;}.pdoc-code .hll{background-color:#ffffcc}.pdoc-code{background:#f8f8f8;}.pdoc-code .c{color:#3D7B7B; font-style:italic}.pdoc-code .err{border:1px solid #FF0000}.pdoc-code .k{color:#008000; font-weight:bold}.pdoc-code .o{color:#666666}.pdoc-code .ch{color:#3D7B7B; font-style:italic}.pdoc-code .cm{color:#3D7B7B; font-style:italic}.pdoc-code .cp{color:#9C6500}.pdoc-code .cpf{color:#3D7B7B; font-style:italic}.pdoc-code .c1{color:#3D7B7B; font-style:italic}.pdoc-code .cs{color:#3D7B7B; font-style:italic}.pdoc-code .gd{color:#A00000}.pdoc-code .ge{font-style:italic}.pdoc-code .gr{color:#E40000}.pdoc-code .gh{color:#000080; font-weight:bold}.pdoc-code .gi{color:#008400}.pdoc-code .go{color:#717171}.pdoc-code .gp{color:#000080; font-weight:bold}.pdoc-code .gs{font-weight:bold}.pdoc-code .gu{color:#800080; font-weight:bold}.pdoc-code .gt{color:#0044DD}.pdoc-code .kc{color:#008000; font-weight:bold}.pdoc-code .kd{color:#008000; font-weight:bold}.pdoc-code .kn{color:#008000; font-weight:bold}.pdoc-code .kp{color:#008000}.pdoc-code .kr{color:#008000; font-weight:bold}.pdoc-code .kt{color:#B00040}.pdoc-code .m{color:#666666}.pdoc-code .s{color:#BA2121}.pdoc-code .na{color:#687822}.pdoc-code .nb{color:#008000}.pdoc-code .nc{color:#0000FF; font-weight:bold}.pdoc-code .no{color:#880000}.pdoc-code .nd{color:#AA22FF}.pdoc-code .ni{color:#717171; font-weight:bold}.pdoc-code .ne{color:#CB3F38; font-weight:bold}.pdoc-code .nf{color:#0000FF}.pdoc-code .nl{color:#767600}.pdoc-code .nn{color:#0000FF; font-weight:bold}.pdoc-code .nt{color:#008000; font-weight:bold}.pdoc-code .nv{color:#19177C}.pdoc-code .ow{color:#AA22FF; font-weight:bold}.pdoc-code .w{color:#bbbbbb}.pdoc-code .mb{color:#666666}.pdoc-code .mf{color:#666666}.pdoc-code .mh{color:#666666}.pdoc-code .mi{color:#666666}.pdoc-code .mo{color:#666666}.pdoc-code .sa{color:#BA2121}.pdoc-code .sb{color:#BA2121}.pdoc-code .sc{color:#BA2121}.pdoc-code .dl{color:#BA2121}.pdoc-code .sd{color:#BA2121; font-style:italic}.pdoc-code .s2{color:#BA2121}.pdoc-code .se{color:#AA5D1F; font-weight:bold}.pdoc-code .sh{color:#BA2121}.pdoc-code .si{color:#A45A77; font-weight:bold}.pdoc-code .sx{color:#008000}.pdoc-code .sr{color:#A45A77}.pdoc-code .s1{color:#BA2121}.pdoc-code .ss{color:#19177C}.pdoc-code .bp{color:#008000}.pdoc-code .fm{color:#0000FF}.pdoc-code .vc{color:#19177C}.pdoc-code .vg{color:#19177C}.pdoc-code .vi{color:#19177C}.pdoc-code .vm{color:#19177C}.pdoc-code .il{color:#666666}</style> + <style>/*! theme.css */:root{--pdoc-background:#fff;}.pdoc{--text:#212529;--muted:#6c757d;--link:#3660a5;--link-hover:#1659c5;--code:#f8f8f8;--active:#fff598;--accent:#eee;--accent2:#c1c1c1;--nav-hover:rgba(255, 255, 255, 0.5);--name:#0066BB;--def:#008800;--annotation:#007020;}</style> + <style>/*! layout.css */html, body{width:100%;height:100%;}html, main{scroll-behavior:smooth;}body{background-color:var(--pdoc-background);}@media (max-width:769px){#navtoggle{cursor:pointer;position:absolute;width:50px;height:40px;top:1rem;right:1rem;border-color:var(--text);color:var(--text);display:flex;opacity:0.8;}#navtoggle:hover{opacity:1;}#togglestate + div{display:none;}#togglestate:checked + div{display:inherit;}main, header{padding:2rem 3vw;}header + main{margin-top:-3rem;}.git-button{display:none !important;}nav input[type="search"]{max-width:77%;}nav input[type="search"]:first-child{margin-top:-6px;}nav input[type="search"]:valid ~ *{display:none !important;}}@media (min-width:770px){:root{--sidebar-width:clamp(12.5rem, 28vw, 22rem);}nav{position:fixed;overflow:auto;height:100vh;width:var(--sidebar-width);}main, header{padding:3rem 2rem 3rem calc(var(--sidebar-width) + 3rem);width:calc(54rem + var(--sidebar-width));max-width:100%;}header + main{margin-top:-4rem;}#navtoggle{display:none;}}#togglestate{position:absolute;height:0;opacity:0;}nav.pdoc{--pad:clamp(0.5rem, 2vw, 1.75rem);--indent:1.5rem;background-color:var(--accent);border-right:1px solid var(--accent2);box-shadow:0 0 20px rgba(50, 50, 50, .2) inset;padding:0 0 0 var(--pad);overflow-wrap:anywhere;scrollbar-width:thin; scrollbar-color:var(--accent2) transparent }nav.pdoc::-webkit-scrollbar{width:.4rem; }nav.pdoc::-webkit-scrollbar-thumb{background-color:var(--accent2); }nav.pdoc > div{padding:var(--pad) 0;}nav.pdoc .module-list-button{display:inline-flex;align-items:center;color:var(--text);border-color:var(--muted);margin-bottom:1rem;}nav.pdoc .module-list-button:hover{border-color:var(--text);}nav.pdoc input[type=search]{display:block;outline-offset:0;width:calc(100% - var(--pad));}nav.pdoc .logo{max-width:calc(100% - var(--pad));max-height:35vh;display:block;margin:0 auto 1rem;transform:translate(calc(-.5 * var(--pad)), 0);}nav.pdoc ul{list-style:none;padding-left:0;}nav.pdoc > div > ul{margin-left:calc(0px - var(--pad));}nav.pdoc li a{padding:.2rem 0 .2rem calc(var(--pad) + var(--indent));}nav.pdoc > div > ul > li > a{padding-left:var(--pad);}nav.pdoc li{transition:all 100ms;}nav.pdoc li:hover{background-color:var(--nav-hover);}nav.pdoc a, nav.pdoc a:hover{color:var(--text);}nav.pdoc a{display:block;}nav.pdoc > h2:first-of-type{margin-top:1.5rem;}nav.pdoc .class:before{content:"class ";color:var(--muted);}nav.pdoc .function:after{content:"()";color:var(--muted);}nav.pdoc footer:before{content:"";display:block;width:calc(100% - var(--pad));border-top:solid var(--accent2) 1px;margin-top:1.5rem;padding-top:.5rem;}nav.pdoc footer{font-size:small;}</style> + <style>/*! content.css */.pdoc{color:var(--text);box-sizing:border-box;line-height:1.5;background:none;}.pdoc .pdoc-button{display:inline-block;border:solid black 1px;border-radius:2px;font-size:.75rem;padding:calc(0.5em - 1px) 1em;transition:100ms all;}.pdoc .pdoc-alert{padding:1rem 1rem 1rem calc(1.5rem + 24px);border:1px solid transparent;border-radius:.25rem;background-repeat:no-repeat;background-position:1rem center;margin-bottom:1rem;}.pdoc .pdoc-alert > *:last-child{margin-bottom:0;}.pdoc .pdoc-alert-note {color:#084298;background-color:#cfe2ff;border-color:#b6d4fe;background-image:url("data:image/svg+xml,%3Csvg%20xmlns%3D%22http%3A//www.w3.org/2000/svg%22%20width%3D%2224%22%20height%3D%2224%22%20fill%3D%22%23084298%22%20viewBox%3D%220%200%2016%2016%22%3E%3Cpath%20d%3D%22M8%2016A8%208%200%201%200%208%200a8%208%200%200%200%200%2016zm.93-9.412-1%204.705c-.07.34.029.533.304.533.194%200%20.487-.07.686-.246l-.088.416c-.287.346-.92.598-1.465.598-.703%200-1.002-.422-.808-1.319l.738-3.468c.064-.293.006-.399-.287-.47l-.451-.081.082-.381%202.29-.287zM8%205.5a1%201%200%201%201%200-2%201%201%200%200%201%200%202z%22/%3E%3C/svg%3E");}.pdoc .pdoc-alert-warning{color:#664d03;background-color:#fff3cd;border-color:#ffecb5;background-image:url("data:image/svg+xml,%3Csvg%20xmlns%3D%22http%3A//www.w3.org/2000/svg%22%20width%3D%2224%22%20height%3D%2224%22%20fill%3D%22%23664d03%22%20viewBox%3D%220%200%2016%2016%22%3E%3Cpath%20d%3D%22M8.982%201.566a1.13%201.13%200%200%200-1.96%200L.165%2013.233c-.457.778.091%201.767.98%201.767h13.713c.889%200%201.438-.99.98-1.767L8.982%201.566zM8%205c.535%200%20.954.462.9.995l-.35%203.507a.552.552%200%200%201-1.1%200L7.1%205.995A.905.905%200%200%201%208%205zm.002%206a1%201%200%201%201%200%202%201%201%200%200%201%200-2z%22/%3E%3C/svg%3E");}.pdoc .pdoc-alert-danger{color:#842029;background-color:#f8d7da;border-color:#f5c2c7;background-image:url("data:image/svg+xml,%3Csvg%20xmlns%3D%22http%3A//www.w3.org/2000/svg%22%20width%3D%2224%22%20height%3D%2224%22%20fill%3D%22%23842029%22%20viewBox%3D%220%200%2016%2016%22%3E%3Cpath%20d%3D%22M5.52.359A.5.5%200%200%201%206%200h4a.5.5%200%200%201%20.474.658L8.694%206H12.5a.5.5%200%200%201%20.395.807l-7%209a.5.5%200%200%201-.873-.454L6.823%209.5H3.5a.5.5%200%200%201-.48-.641l2.5-8.5z%22/%3E%3C/svg%3E");}.pdoc .visually-hidden{position:absolute !important;width:1px !important;height:1px !important;padding:0 !important;margin:-1px !important;overflow:hidden !important;clip:rect(0, 0, 0, 0) !important;white-space:nowrap !important;border:0 !important;}.pdoc h1, .pdoc h2, .pdoc h3{font-weight:300;margin:.3em 0;padding:.2em 0;}.pdoc > section:not(.module-info) h1{font-size:1.5rem;font-weight:500;}.pdoc > section:not(.module-info) h2{font-size:1.4rem;font-weight:500;}.pdoc > section:not(.module-info) h3{font-size:1.3rem;font-weight:500;}.pdoc > section:not(.module-info) h4{font-size:1.2rem;}.pdoc > section:not(.module-info) h5{font-size:1.1rem;}.pdoc a{text-decoration:none;color:var(--link);}.pdoc a:hover{color:var(--link-hover);}.pdoc blockquote{margin-left:2rem;}.pdoc pre{border-top:1px solid var(--accent2);border-bottom:1px solid var(--accent2);margin-top:0;margin-bottom:1em;padding:.5rem 0 .5rem .5rem;overflow-x:auto;background-color:var(--code);}.pdoc code{color:var(--text);padding:.2em .4em;margin:0;font-size:85%;background-color:var(--code);border-radius:6px;}.pdoc a > code{color:inherit;}.pdoc pre > code{display:inline-block;font-size:inherit;background:none;border:none;padding:0;}.pdoc > section:not(.module-info){margin-bottom:1.5rem;}.pdoc .modulename{margin-top:0;font-weight:bold;}.pdoc .modulename a{color:var(--link);transition:100ms all;}.pdoc .git-button{float:right;border:solid var(--link) 1px;}.pdoc .git-button:hover{background-color:var(--link);color:var(--pdoc-background);}.view-source-toggle-state,.view-source-toggle-state ~ .pdoc-code{display:none;}.view-source-toggle-state:checked ~ .pdoc-code{display:block;}.view-source-button{display:inline-block;float:right;font-size:.75rem;line-height:1.5rem;color:var(--muted);padding:0 .4rem 0 1.3rem;cursor:pointer;text-indent:-2px;}.view-source-button > span{visibility:hidden;}.module-info .view-source-button{float:none;display:flex;justify-content:flex-end;margin:-1.2rem .4rem -.2rem 0;}.view-source-button::before{position:absolute;content:"View Source";display:list-item;list-style-type:disclosure-closed;}.view-source-toggle-state:checked ~ .attr .view-source-button::before,.view-source-toggle-state:checked ~ .view-source-button::before{list-style-type:disclosure-open;}.pdoc .docstring{margin-bottom:1.5rem;}.pdoc section:not(.module-info) .docstring{margin-left:clamp(0rem, 5vw - 2rem, 1rem);}.pdoc .docstring .pdoc-code{margin-left:1em;margin-right:1em;}.pdoc h1:target,.pdoc h2:target,.pdoc h3:target,.pdoc h4:target,.pdoc h5:target,.pdoc h6:target,.pdoc .pdoc-code > pre > span:target{background-color:var(--active);box-shadow:-1rem 0 0 0 var(--active);}.pdoc .pdoc-code > pre > span:target{display:block;}.pdoc div:target > .attr,.pdoc section:target > .attr,.pdoc dd:target > a{background-color:var(--active);}.pdoc *{scroll-margin:2rem;}.pdoc .pdoc-code .linenos{user-select:none;}.pdoc .attr:hover{filter:contrast(0.95);}.pdoc section, .pdoc .classattr{position:relative;}.pdoc .headerlink{--width:clamp(1rem, 3vw, 2rem);position:absolute;top:0;left:calc(0rem - var(--width));transition:all 100ms ease-in-out;opacity:0;}.pdoc .headerlink::before{content:"#";display:block;text-align:center;width:var(--width);height:2.3rem;line-height:2.3rem;font-size:1.5rem;}.pdoc .attr:hover ~ .headerlink,.pdoc *:target > .headerlink,.pdoc .headerlink:hover{opacity:1;}.pdoc .attr{display:block;margin:.5rem 0 .5rem;padding:.4rem .4rem .4rem 1rem;background-color:var(--accent);overflow-x:auto;}.pdoc .classattr{margin-left:2rem;}.pdoc .name{color:var(--name);font-weight:bold;}.pdoc .def{color:var(--def);font-weight:bold;}.pdoc .signature{background-color:transparent;}.pdoc .param, .pdoc .return-annotation{white-space:pre;}.pdoc .signature.multiline .param{display:block;}.pdoc .signature.condensed .param{display:inline-block;}.pdoc .annotation{color:var(--annotation);}.pdoc .inherited{margin-left:2rem;}.pdoc .inherited dt{font-weight:700;}.pdoc .inherited dt, .pdoc .inherited dd{display:inline;margin-left:0;margin-bottom:.5rem;}.pdoc .inherited dd:not(:last-child):after{content:", ";}.pdoc .inherited .class:before{content:"class ";}.pdoc .inherited .function a:after{content:"()";}.pdoc .search-result .docstring{overflow:auto;max-height:25vh;}.pdoc .search-result.focused > .attr{background-color:var(--active);}.pdoc .attribution{margin-top:2rem;display:block;opacity:0.5;transition:all 200ms;filter:grayscale(100%);}.pdoc .attribution:hover{opacity:1;filter:grayscale(0%);}.pdoc .attribution img{margin-left:5px;height:35px;vertical-align:middle;width:70px;transition:all 200ms;}.pdoc table{display:block;width:max-content;max-width:100%;overflow:auto;margin-bottom:1rem;}.pdoc table th{font-weight:600;}.pdoc table th, .pdoc table td{padding:6px 13px;border:1px solid var(--accent2);}</style> + <style>/*! custom.css */</style></head> +<body> + <nav class="pdoc"> + <label id="navtoggle" for="togglestate" class="pdoc-button"><svg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 30 30'><path stroke-linecap='round' stroke="currentColor" stroke-miterlimit='10' stroke-width='2' d='M4 7h22M4 15h22M4 23h22'/></svg></label> + <input id="togglestate" type="checkbox" aria-hidden="true" tabindex="-1"> + <div> <a class="pdoc-button module-list-button" href="../sqlglot.html"> +<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="bi bi-box-arrow-in-left" viewBox="0 0 16 16"> + <path fill-rule="evenodd" d="M10 3.5a.5.5 0 0 0-.5-.5h-8a.5.5 0 0 0-.5.5v9a.5.5 0 0 0 .5.5h8a.5.5 0 0 0 .5-.5v-2a.5.5 0 0 1 1 0v2A1.5 1.5 0 0 1 9.5 14h-8A1.5 1.5 0 0 1 0 12.5v-9A1.5 1.5 0 0 1 1.5 2h8A1.5 1.5 0 0 1 11 3.5v2a.5.5 0 0 1-1 0v-2z"/> + <path fill-rule="evenodd" d="M4.146 8.354a.5.5 0 0 1 0-.708l3-3a.5.5 0 1 1 .708.708L5.707 7.5H14.5a.5.5 0 0 1 0 1H5.707l2.147 2.146a.5.5 0 0 1-.708.708l-3-3z"/> +</svg> sqlglot</a> + + + <input type="search" placeholder="Search..." role="searchbox" aria-label="search" + pattern=".+" required> + + <h2>Contents</h2> + <ul> + <li><a href="#pyspark-dataframe-sql-generator">PySpark DataFrame SQL Generator</a></li> + <li><a href="#how-to-use">How to use</a> + <ul> + <li><a href="#instructions">Instructions</a></li> + <li><a href="#examples">Examples</a></li> + <li><a href="#registering-custom-schema-class">Registering Custom Schema Class</a></li> + <li><a href="#example-implementations">Example Implementations</a></li> + </ul></li> + <li><a href="#unsupportable-operations">Unsupportable Operations</a></li> +</ul> + + + <h2>Submodules</h2> + <ul> + <li><a href="dataframe/sql.html">sql</a></li> + </ul> + + + <footer>Copyright (c) 2023 Toby Mao</footer> + + <a class="attribution" title="pdoc: Python API documentation generator" href="https://pdoc.dev" target="_blank"> + built with <span class="visually-hidden">pdoc</span><img + alt="pdoc logo" + src="data:image/svg+xml,%3Csvg%20xmlns%3D%22http%3A//www.w3.org/2000/svg%22%20role%3D%22img%22%20aria-label%3D%22pdoc%20logo%22%20width%3D%22300%22%20height%3D%22150%22%20viewBox%3D%22-1%200%2060%2030%22%3E%3Ctitle%3Epdoc%3C/title%3E%3Cpath%20d%3D%22M29.621%2021.293c-.011-.273-.214-.475-.511-.481a.5.5%200%200%200-.489.503l-.044%201.393c-.097.551-.695%201.215-1.566%201.704-.577.428-1.306.486-2.193.182-1.426-.617-2.467-1.654-3.304-2.487l-.173-.172a3.43%203.43%200%200%200-.365-.306.49.49%200%200%200-.286-.196c-1.718-1.06-4.931-1.47-7.353.191l-.219.15c-1.707%201.187-3.413%202.131-4.328%201.03-.02-.027-.49-.685-.141-1.763.233-.721.546-2.408.772-4.076.042-.09.067-.187.046-.288.166-1.347.277-2.625.241-3.351%201.378-1.008%202.271-2.586%202.271-4.362%200-.976-.272-1.935-.788-2.774-.057-.094-.122-.18-.184-.268.033-.167.052-.339.052-.516%200-1.477-1.202-2.679-2.679-2.679-.791%200-1.496.352-1.987.9a6.3%206.3%200%200%200-1.001.029c-.492-.564-1.207-.929-2.012-.929-1.477%200-2.679%201.202-2.679%202.679A2.65%202.65%200%200%200%20.97%206.554c-.383.747-.595%201.572-.595%202.41%200%202.311%201.507%204.29%203.635%205.107-.037.699-.147%202.27-.423%203.294l-.137.461c-.622%202.042-2.515%208.257%201.727%2010.643%201.614.908%203.06%201.248%204.317%201.248%202.665%200%204.492-1.524%205.322-2.401%201.476-1.559%202.886-1.854%206.491.82%201.877%201.393%203.514%201.753%204.861%201.068%202.223-1.713%202.811-3.867%203.399-6.374.077-.846.056-1.469.054-1.537zm-4.835%204.313c-.054.305-.156.586-.242.629-.034-.007-.131-.022-.307-.157-.145-.111-.314-.478-.456-.908.221.121.432.25.675.355.115.039.219.051.33.081zm-2.251-1.238c-.05.33-.158.648-.252.694-.022.001-.125-.018-.307-.157-.217-.166-.488-.906-.639-1.573.358.344.754.693%201.198%201.036zm-3.887-2.337c-.006-.116-.018-.231-.041-.342.635.145%201.189.368%201.599.625.097.231.166.481.174.642-.03.049-.055.101-.067.158-.046.013-.128.026-.298.004-.278-.037-.901-.57-1.367-1.087zm-1.127-.497c.116.306.176.625.12.71-.019.014-.117.045-.345.016-.206-.027-.604-.332-.986-.695.41-.051.816-.056%201.211-.031zm-4.535%201.535c.209.22.379.47.358.598-.006.041-.088.138-.351.234-.144.055-.539-.063-.979-.259a11.66%2011.66%200%200%200%20.972-.573zm.983-.664c.359-.237.738-.418%201.126-.554.25.237.479.548.457.694-.006.042-.087.138-.351.235-.174.064-.694-.105-1.232-.375zm-3.381%201.794c-.022.145-.061.29-.149.401-.133.166-.358.248-.69.251h-.002c-.133%200-.306-.26-.45-.621.417.091.854.07%201.291-.031zm-2.066-8.077a4.78%204.78%200%200%201-.775-.584c.172-.115.505-.254.88-.378l-.105.962zm-.331%202.302a10.32%2010.32%200%200%201-.828-.502c.202-.143.576-.328.984-.49l-.156.992zm-.45%202.157l-.701-.403c.214-.115.536-.249.891-.376a11.57%2011.57%200%200%201-.19.779zm-.181%201.716c.064.398.194.702.298.893-.194-.051-.435-.162-.736-.398.061-.119.224-.3.438-.495zM8.87%204.141c0%20.152-.123.276-.276.276s-.275-.124-.275-.276.123-.276.276-.276.275.124.275.276zm-.735-.389a1.15%201.15%200%200%200-.314.783%201.16%201.16%200%200%200%201.162%201.162c.457%200%20.842-.27%201.032-.653.026.117.042.238.042.362a1.68%201.68%200%200%201-1.679%201.679%201.68%201.68%200%200%201-1.679-1.679c0-.843.626-1.535%201.436-1.654zM5.059%205.406A1.68%201.68%200%200%201%203.38%207.085a1.68%201.68%200%200%201-1.679-1.679c0-.037.009-.072.011-.109.21.3.541.508.935.508a1.16%201.16%200%200%200%201.162-1.162%201.14%201.14%200%200%200-.474-.912c.015%200%20.03-.005.045-.005.926.001%201.679.754%201.679%201.68zM3.198%204.141c0%20.152-.123.276-.276.276s-.275-.124-.275-.276.123-.276.276-.276.275.124.275.276zM1.375%208.964c0-.52.103-1.035.288-1.52.466.394%201.06.64%201.717.64%201.144%200%202.116-.725%202.499-1.738.383%201.012%201.355%201.738%202.499%201.738.867%200%201.631-.421%202.121-1.062.307.605.478%201.267.478%201.942%200%202.486-2.153%204.51-4.801%204.51s-4.801-2.023-4.801-4.51zm24.342%2019.349c-.985.498-2.267.168-3.813-.979-3.073-2.281-5.453-3.199-7.813-.705-1.315%201.391-4.163%203.365-8.423.97-3.174-1.786-2.239-6.266-1.261-9.479l.146-.492c.276-1.02.395-2.457.444-3.268a6.11%206.11%200%200%200%201.18.115%206.01%206.01%200%200%200%202.536-.562l-.006.175c-.802.215-1.848.612-2.021%201.25-.079.295.021.601.274.837.219.203.415.364.598.501-.667.304-1.243.698-1.311%201.179-.02.144-.022.507.393.787.213.144.395.26.564.365-1.285.521-1.361.96-1.381%201.126-.018.142-.011.496.427.746l.854.489c-.473.389-.971.914-.999%201.429-.018.278.095.532.316.713.675.556%201.231.721%201.653.721.059%200%20.104-.014.158-.02.207.707.641%201.64%201.513%201.64h.013c.8-.008%201.236-.345%201.462-.626.173-.216.268-.457.325-.692.424.195.93.374%201.372.374.151%200%20.294-.021.423-.068.732-.27.944-.704.993-1.021.009-.061.003-.119.002-.179.266.086.538.147.789.147.15%200%20.294-.021.423-.069.542-.2.797-.489.914-.754.237.147.478.258.704.288.106.014.205.021.296.021.356%200%20.595-.101.767-.229.438.435%201.094.992%201.656%201.067.106.014.205.021.296.021a1.56%201.56%200%200%200%20.323-.035c.17.575.453%201.289.866%201.605.358.273.665.362.914.362a.99.99%200%200%200%20.421-.093%201.03%201.03%200%200%200%20.245-.164c.168.428.39.846.68%201.068.358.273.665.362.913.362a.99.99%200%200%200%20.421-.093c.317-.148.512-.448.639-.762.251.157.495.257.726.257.127%200%20.25-.024.37-.071.427-.17.706-.617.841-1.314.022-.015.047-.022.068-.038.067-.051.133-.104.196-.159-.443%201.486-1.107%202.761-2.086%203.257zM8.66%209.925a.5.5%200%201%200-1%200c0%20.653-.818%201.205-1.787%201.205s-1.787-.552-1.787-1.205a.5.5%200%201%200-1%200c0%201.216%201.25%202.205%202.787%202.205s2.787-.989%202.787-2.205zm4.4%2015.965l-.208.097c-2.661%201.258-4.708%201.436-6.086.527-1.542-1.017-1.88-3.19-1.844-4.198a.4.4%200%200%200-.385-.414c-.242-.029-.406.164-.414.385-.046%201.249.367%203.686%202.202%204.896.708.467%201.547.7%202.51.7%201.248%200%202.706-.392%204.362-1.174l.185-.086a.4.4%200%200%200%20.205-.527c-.089-.204-.326-.291-.527-.206zM9.547%202.292c.093.077.205.114.317.114a.5.5%200%200%200%20.318-.886L8.817.397a.5.5%200%200%200-.703.068.5.5%200%200%200%20.069.703l1.364%201.124zm-7.661-.065c.086%200%20.173-.022.253-.068l1.523-.893a.5.5%200%200%200-.506-.863l-1.523.892a.5.5%200%200%200-.179.685c.094.158.261.247.432.247z%22%20transform%3D%22matrix%28-1%200%200%201%2058%200%29%22%20fill%3D%22%233bb300%22/%3E%3Cpath%20d%3D%22M.3%2021.86V10.18q0-.46.02-.68.04-.22.18-.5.28-.54%201.34-.54%201.06%200%201.42.28.38.26.44.78.76-1.04%202.38-1.04%201.64%200%203.1%201.54%201.46%201.54%201.46%203.58%200%202.04-1.46%203.58-1.44%201.54-3.08%201.54-1.64%200-2.38-.92v4.04q0%20.46-.04.68-.02.22-.18.5-.14.3-.5.42-.36.12-.98.12-.62%200-1-.12-.36-.12-.52-.4-.14-.28-.18-.5-.02-.22-.02-.68zm3.96-9.42q-.46.54-.46%201.18%200%20.64.46%201.18.48.52%201.2.52.74%200%201.24-.52.52-.52.52-1.18%200-.66-.48-1.18-.48-.54-1.26-.54-.76%200-1.22.54zm14.741-8.36q.16-.3.54-.42.38-.12%201-.12.64%200%201.02.12.38.12.52.42.16.3.18.54.04.22.04.68v11.94q0%20.46-.04.7-.02.22-.18.5-.3.54-1.7.54-1.38%200-1.54-.98-.84.96-2.34.96-1.8%200-3.28-1.56-1.48-1.58-1.48-3.66%200-2.1%201.48-3.68%201.5-1.58%203.28-1.58%201.48%200%202.3%201v-4.2q0-.46.02-.68.04-.24.18-.52zm-3.24%2010.86q.52.54%201.26.54.74%200%201.22-.54.5-.54.5-1.18%200-.66-.48-1.22-.46-.56-1.26-.56-.8%200-1.28.56-.48.54-.48%201.2%200%20.66.52%201.2zm7.833-1.2q0-2.4%201.68-3.96%201.68-1.56%203.84-1.56%202.16%200%203.82%201.56%201.66%201.54%201.66%203.94%200%201.66-.86%202.96-.86%201.28-2.1%201.9-1.22.6-2.54.6-1.32%200-2.56-.64-1.24-.66-2.1-1.92-.84-1.28-.84-2.88zm4.18%201.44q.64.48%201.3.48.66%200%201.32-.5.66-.5.66-1.48%200-.98-.62-1.46-.62-.48-1.34-.48-.72%200-1.34.5-.62.5-.62%201.48%200%20.96.64%201.46zm11.412-1.44q0%20.84.56%201.32.56.46%201.18.46.64%200%201.18-.36.56-.38.9-.38.6%200%201.46%201.06.46.58.46%201.04%200%20.76-1.1%201.42-1.14.8-2.8.8-1.86%200-3.58-1.34-.82-.64-1.34-1.7-.52-1.08-.52-2.36%200-1.3.52-2.34.52-1.06%201.34-1.7%201.66-1.32%203.54-1.32.76%200%201.48.22.72.2%201.06.4l.32.2q.36.24.56.38.52.4.52.92%200%20.5-.42%201.14-.72%201.1-1.38%201.1-.38%200-1.08-.44-.36-.34-1.04-.34-.66%200-1.24.48-.58.48-.58%201.34z%22%20fill%3D%22green%22/%3E%3C/svg%3E"/> + </a> +</div> + </nav> + <main class="pdoc"> + <section class="module-info"> + <a class="pdoc-button git-button" href="https://github.com/tobymao/sqlglot/tree/main/sqlglot/dataframe/__init__.py">Edit on GitHub</a> + + <div class="docstring"><h1 id="pyspark-dataframe-sql-generator">PySpark DataFrame SQL Generator</h1> + +<p>This is a drop-in replacement for the PySpark DataFrame API that will generate SQL instead of executing DataFrame operations directly. This, when combined with the transpiling support in SQLGlot, allows one to write PySpark DataFrame code and execute it on other engines like <a href="https://duckdb.org/">DuckDB</a>, <a href="https://prestodb.io/">Presto</a>, <a href="https://spark.apache.org/">Spark</a>, <a href="https://www.snowflake.com/en/">Snowflake</a>, and <a href="https://cloud.google.com/bigquery/">BigQuery</a>. </p> + +<p>Currently many of the common operations are covered and more functionality will be added over time. Please <a href="https://github.com/tobymao/sqlglot/issues">open an issue</a> or <a href="https://github.com/tobymao/sqlglot/pulls">PR</a> with your feedback or contribution to help influence what should be prioritized next and make sure your use case is properly supported.</p> + +<h1 id="how-to-use">How to use</h1> + +<h2 id="instructions">Instructions</h2> + +<ul> +<li><a href="https://github.com/tobymao/sqlglot/blob/main/README.md#install">Install SQLGlot</a> and that is all that is required to just generate SQL. <a href="#examples">The examples</a> show generating SQL and then executing that SQL on a specific engine and that will require that engine's client library.</li> +<li>Find/replace all <code>from pyspark.sql</code> with <code>from <a href="">sqlglot.dataframe</a></code>.</li> +<li>Prior to any <code>spark.read.table</code> or <code>spark.table</code> run <code>sqlglot.schema.add_table('<table_name>', <column_structure>)</code>. +<ul> +<li>The column structure can be defined the following ways: +<ul> +<li>Dictionary where the keys are column names and values are string of the Spark SQL type name. +<ul> +<li>Ex: <code>{'cola': 'string', 'colb': 'int'}</code></li> +</ul></li> +<li>PySpark DataFrame <code>StructType</code> similar to when using <code>createDataFrame</code>. +<ul> +<li>Ex: <code>StructType([StructField('cola', StringType()), StructField('colb', IntegerType())])</code></li> +</ul></li> +<li>A string of names and types similar to what is supported in <code>createDataFrame</code>. +<ul> +<li>Ex: <code>cola: STRING, colb: INT</code></li> +</ul></li> +<li>[Not Recommended] A list of string column names without type. +<ul> +<li>Ex: <code>['cola', 'colb']</code></li> +<li>The lack of types may limit functionality in future releases.</li> +</ul></li> +</ul></li> +<li>See <a href="#registering-custom-schema-class">Registering Custom Schema</a> for information on how to skip this step if the information is stored externally.</li> +</ul></li> +<li>Add <code>.sql(pretty=True)</code> to your final DataFrame command to return a list of sql statements to run that command. +<ul> +<li>In most cases a single SQL statement is returned. Currently the only exception is when caching DataFrames which isn't supported in other dialects. </li> +<li>Spark is the default output dialect. See <a href="https://github.com/tobymao/sqlglot/tree/main/sqlglot/dialects">dialects</a> for a full list of dialects.</li> +<li>Ex: <code>.sql(pretty=True, dialect='bigquery')</code></li> +</ul></li> +</ul> + +<h2 id="examples">Examples</h2> + +<div class="pdoc-code codehilite"> +<pre><span></span><code><span class="kn">import</span> <span class="nn">sqlglot</span> +<span class="kn">from</span> <span class="nn">sqlglot.dataframe.sql.session</span> <span class="kn">import</span> <span class="n">SparkSession</span> +<span class="kn">from</span> <span class="nn"><a href="dataframe/sql.html">sqlglot.dataframe.sql</a></span> <span class="kn">import</span> <span class="n">functions</span> <span class="k">as</span> <span class="n">F</span> + +<span class="n">sqlglot</span><span class="o">.</span><span class="n">schema</span><span class="o">.</span><span class="n">add_table</span><span class="p">(</span><span class="s1">'employee'</span><span class="p">,</span> <span class="p">{</span> + <span class="s1">'employee_id'</span><span class="p">:</span> <span class="s1">'INT'</span><span class="p">,</span> + <span class="s1">'fname'</span><span class="p">:</span> <span class="s1">'STRING'</span><span class="p">,</span> + <span class="s1">'lname'</span><span class="p">:</span> <span class="s1">'STRING'</span><span class="p">,</span> + <span class="s1">'age'</span><span class="p">:</span> <span class="s1">'INT'</span><span class="p">,</span> +<span class="p">})</span> <span class="c1"># Register the table structure prior to reading from the table</span> + +<span class="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="p">()</span> + +<span class="n">df</span> <span class="o">=</span> <span class="p">(</span> + <span class="n">spark</span> + <span class="o">.</span><span class="n">table</span><span class="p">(</span><span class="s1">'employee'</span><span class="p">)</span> + <span class="o">.</span><span class="n">groupBy</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">col</span><span class="p">(</span><span class="s2">"age"</span><span class="p">))</span> + <span class="o">.</span><span class="n">agg</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">countDistinct</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">col</span><span class="p">(</span><span class="s2">"employee_id"</span><span class="p">))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"num_employees"</span><span class="p">))</span> +<span class="p">)</span> + +<span class="nb">print</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">sql</span><span class="p">(</span><span class="n">pretty</span><span class="o">=</span><span class="kc">True</span><span class="p">))</span> <span class="c1"># Spark will be the dialect used by default</span> +</code></pre> +</div> + +<pre><code>SELECT + `employee`.`age` AS `age`, + COUNT(DISTINCT `employee`.`employee_id`) AS `num_employees` +FROM `employee` AS `employee` +GROUP BY + `employee`.`age` +</code></pre> + +<h2 id="registering-custom-schema-class">Registering Custom Schema Class</h2> + +<p>The step of adding <code>sqlglot.schema.add_table</code> can be skipped if you have the column structure stored externally like in a file or from an external metadata table. This can be done by writing a class that implements the <code><a href="schema.html#Schema">sqlglot.schema.Schema</a></code> abstract class and then assigning that class to <code><a href="schema.html">sqlglot.schema</a></code>. </p> + +<div class="pdoc-code codehilite"> +<pre><span></span><code><span class="kn">import</span> <span class="nn">sqlglot</span> +<span class="kn">from</span> <span class="nn">sqlglot.dataframe.sql.session</span> <span class="kn">import</span> <span class="n">SparkSession</span> +<span class="kn">from</span> <span class="nn"><a href="dataframe/sql.html">sqlglot.dataframe.sql</a></span> <span class="kn">import</span> <span class="n">functions</span> <span class="k">as</span> <span class="n">F</span> +<span class="kn">from</span> <span class="nn"><a href="schema.html">sqlglot.schema</a></span> <span class="kn">import</span> <span class="n">Schema</span> + + +<span class="k">class</span> <span class="nc">ExternalSchema</span><span class="p">(</span><span class="n">Schema</span><span class="p">):</span> + <span class="o">...</span> + +<span class="n"><a href="schema.html">sqlglot.schema</a></span> <span class="o">=</span> <span class="n">ExternalSchema</span><span class="p">()</span> + +<span class="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="p">()</span> + +<span class="n">df</span> <span class="o">=</span> <span class="p">(</span> + <span class="n">spark</span> + <span class="o">.</span><span class="n">table</span><span class="p">(</span><span class="s1">'employee'</span><span class="p">)</span> + <span class="o">.</span><span class="n">groupBy</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">col</span><span class="p">(</span><span class="s2">"age"</span><span class="p">))</span> + <span class="o">.</span><span class="n">agg</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">countDistinct</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">col</span><span class="p">(</span><span class="s2">"employee_id"</span><span class="p">))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"num_employees"</span><span class="p">))</span> +<span class="p">)</span> + +<span class="nb">print</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">sql</span><span class="p">(</span><span class="n">pretty</span><span class="o">=</span><span class="kc">True</span><span class="p">))</span> +</code></pre> +</div> + +<h2 id="example-implementations">Example Implementations</h2> + +<h3 id="bigquery">Bigquery</h3> + +<div class="pdoc-code codehilite"> +<pre><span></span><code><span class="kn">from</span> <span class="nn">google.cloud</span> <span class="kn">import</span> <span class="n">bigquery</span> +<span class="kn">from</span> <span class="nn">sqlglot.dataframe.sql.session</span> <span class="kn">import</span> <span class="n">SparkSession</span> +<span class="kn">from</span> <span class="nn"><a href="dataframe/sql.html">sqlglot.dataframe.sql</a></span> <span class="kn">import</span> <span class="n">types</span> +<span class="kn">from</span> <span class="nn"><a href="dataframe/sql.html">sqlglot.dataframe.sql</a></span> <span class="kn">import</span> <span class="n">functions</span> <span class="k">as</span> <span class="n">F</span> + +<span class="n">client</span> <span class="o">=</span> <span class="n">bigquery</span><span class="o">.</span><span class="n">Client</span><span class="p">()</span> + +<span class="n">data</span> <span class="o">=</span> <span class="p">[</span> + <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="s2">"Jack"</span><span class="p">,</span> <span class="s2">"Shephard"</span><span class="p">,</span> <span class="mi">34</span><span class="p">),</span> + <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="s2">"John"</span><span class="p">,</span> <span class="s2">"Locke"</span><span class="p">,</span> <span class="mi">48</span><span class="p">),</span> + <span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="s2">"Kate"</span><span class="p">,</span> <span class="s2">"Austen"</span><span class="p">,</span> <span class="mi">34</span><span class="p">),</span> + <span class="p">(</span><span class="mi">4</span><span class="p">,</span> <span class="s2">"Claire"</span><span class="p">,</span> <span class="s2">"Littleton"</span><span class="p">,</span> <span class="mi">22</span><span class="p">),</span> + <span class="p">(</span><span class="mi">5</span><span class="p">,</span> <span class="s2">"Hugo"</span><span class="p">,</span> <span class="s2">"Reyes"</span><span class="p">,</span> <span class="mi">26</span><span class="p">),</span> +<span class="p">]</span> +<span class="n">schema</span> <span class="o">=</span> <span class="n">types</span><span class="o">.</span><span class="n">StructType</span><span class="p">([</span> + <span class="n">types</span><span class="o">.</span><span class="n">StructField</span><span class="p">(</span><span class="s1">'employee_id'</span><span class="p">,</span> <span class="n">types</span><span class="o">.</span><span class="n">IntegerType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> + <span class="n">types</span><span class="o">.</span><span class="n">StructField</span><span class="p">(</span><span class="s1">'fname'</span><span class="p">,</span> <span class="n">types</span><span class="o">.</span><span class="n">StringType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> + <span class="n">types</span><span class="o">.</span><span class="n">StructField</span><span class="p">(</span><span class="s1">'lname'</span><span class="p">,</span> <span class="n">types</span><span class="o">.</span><span class="n">StringType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> + <span class="n">types</span><span class="o">.</span><span class="n">StructField</span><span class="p">(</span><span class="s1">'age'</span><span class="p">,</span> <span class="n">types</span><span class="o">.</span><span class="n">IntegerType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> +<span class="p">])</span> + +<span class="n">sql_statements</span> <span class="o">=</span> <span class="p">(</span> + <span class="n">SparkSession</span><span class="p">()</span> + <span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">schema</span><span class="p">)</span> + <span class="o">.</span><span class="n">groupBy</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">col</span><span class="p">(</span><span class="s2">"age"</span><span class="p">))</span> + <span class="o">.</span><span class="n">agg</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">countDistinct</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">col</span><span class="p">(</span><span class="s2">"employee_id"</span><span class="p">))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"num_employees"</span><span class="p">))</span> + <span class="o">.</span><span class="n">sql</span><span class="p">(</span><span class="n">dialect</span><span class="o">=</span><span class="s2">"bigquery"</span><span class="p">)</span> +<span class="p">)</span> + +<span class="n">result</span> <span class="o">=</span> <span class="kc">None</span> +<span class="k">for</span> <span class="n">sql</span> <span class="ow">in</span> <span class="n">sql_statements</span><span class="p">:</span> + <span class="n">result</span> <span class="o">=</span> <span class="n">client</span><span class="o">.</span><span class="n">query</span><span class="p">(</span><span class="n">sql</span><span class="p">)</span> + +<span class="k">assert</span> <span class="n">result</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> +<span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">client</span><span class="o">.</span><span class="n">query</span><span class="p">(</span><span class="n">result</span><span class="p">):</span> + <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Age: </span><span class="si">{</span><span class="n">row</span><span class="p">[</span><span class="s1">'age'</span><span class="p">]</span><span class="si">}</span><span class="s2">, Num Employees: </span><span class="si">{</span><span class="n">row</span><span class="p">[</span><span class="s1">'num_employees'</span><span class="p">]</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span> +</code></pre> +</div> + +<h3 id="snowflake">Snowflake</h3> + +<div class="pdoc-code codehilite"> +<pre><span></span><code><span class="kn">import</span> <span class="nn">os</span> + +<span class="kn">import</span> <span class="nn">snowflake.connector</span> +<span class="kn">from</span> <span class="nn">sqlglot.dataframe.session</span> <span class="kn">import</span> <span class="n">SparkSession</span> +<span class="kn">from</span> <span class="nn"><a href="">sqlglot.dataframe</a></span> <span class="kn">import</span> <span class="n">types</span> +<span class="kn">from</span> <span class="nn"><a href="">sqlglot.dataframe</a></span> <span class="kn">import</span> <span class="n">functions</span> <span class="k">as</span> <span class="n">F</span> + +<span class="n">ctx</span> <span class="o">=</span> <span class="n">snowflake</span><span class="o">.</span><span class="n">connector</span><span class="o">.</span><span class="n">connect</span><span class="p">(</span> + <span class="n">user</span><span class="o">=</span><span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s2">"SNOWFLAKE_USER"</span><span class="p">],</span> + <span class="n">password</span><span class="o">=</span><span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s2">"SNOWFLAKE_PASS"</span><span class="p">],</span> + <span class="n">account</span><span class="o">=</span><span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s2">"SNOWFLAKE_ACCOUNT"</span><span class="p">]</span> +<span class="p">)</span> +<span class="n">cs</span> <span class="o">=</span> <span class="n">ctx</span><span class="o">.</span><span class="n">cursor</span><span class="p">()</span> + +<span class="n">data</span> <span class="o">=</span> <span class="p">[</span> + <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="s2">"Jack"</span><span class="p">,</span> <span class="s2">"Shephard"</span><span class="p">,</span> <span class="mi">34</span><span class="p">),</span> + <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="s2">"John"</span><span class="p">,</span> <span class="s2">"Locke"</span><span class="p">,</span> <span class="mi">48</span><span class="p">),</span> + <span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="s2">"Kate"</span><span class="p">,</span> <span class="s2">"Austen"</span><span class="p">,</span> <span class="mi">34</span><span class="p">),</span> + <span class="p">(</span><span class="mi">4</span><span class="p">,</span> <span class="s2">"Claire"</span><span class="p">,</span> <span class="s2">"Littleton"</span><span class="p">,</span> <span class="mi">22</span><span class="p">),</span> + <span class="p">(</span><span class="mi">5</span><span class="p">,</span> <span class="s2">"Hugo"</span><span class="p">,</span> <span class="s2">"Reyes"</span><span class="p">,</span> <span class="mi">26</span><span class="p">),</span> +<span class="p">]</span> +<span class="n">schema</span> <span class="o">=</span> <span class="n">types</span><span class="o">.</span><span class="n">StructType</span><span class="p">([</span> + <span class="n">types</span><span class="o">.</span><span class="n">StructField</span><span class="p">(</span><span class="s1">'employee_id'</span><span class="p">,</span> <span class="n">types</span><span class="o">.</span><span class="n">IntegerType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> + <span class="n">types</span><span class="o">.</span><span class="n">StructField</span><span class="p">(</span><span class="s1">'fname'</span><span class="p">,</span> <span class="n">types</span><span class="o">.</span><span class="n">StringType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> + <span class="n">types</span><span class="o">.</span><span class="n">StructField</span><span class="p">(</span><span class="s1">'lname'</span><span class="p">,</span> <span class="n">types</span><span class="o">.</span><span class="n">StringType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> + <span class="n">types</span><span class="o">.</span><span class="n">StructField</span><span class="p">(</span><span class="s1">'age'</span><span class="p">,</span> <span class="n">types</span><span class="o">.</span><span class="n">IntegerType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> +<span class="p">])</span> + +<span class="n">sql_statements</span> <span class="o">=</span> <span class="p">(</span> + <span class="n">SparkSession</span><span class="p">()</span> + <span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">schema</span><span class="p">)</span> + <span class="o">.</span><span class="n">groupBy</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">col</span><span class="p">(</span><span class="s2">"age"</span><span class="p">))</span> + <span class="o">.</span><span class="n">agg</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">countDistinct</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">col</span><span class="p">(</span><span class="s2">"lname"</span><span class="p">))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"num_employees"</span><span class="p">))</span> + <span class="o">.</span><span class="n">sql</span><span class="p">(</span><span class="n">dialect</span><span class="o">=</span><span class="s2">"snowflake"</span><span class="p">)</span> +<span class="p">)</span> + +<span class="k">try</span><span class="p">:</span> + <span class="k">for</span> <span class="n">sql</span> <span class="ow">in</span> <span class="n">sql_statements</span><span class="p">:</span> + <span class="n">cs</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">sql</span><span class="p">)</span> + <span class="n">results</span> <span class="o">=</span> <span class="n">cs</span><span class="o">.</span><span class="n">fetchall</span><span class="p">()</span> + <span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">results</span><span class="p">:</span> + <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Age: </span><span class="si">{</span><span class="n">row</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="si">}</span><span class="s2">, Num Employees: </span><span class="si">{</span><span class="n">row</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span> +<span class="k">finally</span><span class="p">:</span> + <span class="n">cs</span><span class="o">.</span><span class="n">close</span><span class="p">()</span> +<span class="n">ctx</span><span class="o">.</span><span class="n">close</span><span class="p">()</span> +</code></pre> +</div> + +<h3 id="spark">Spark</h3> + +<div class="pdoc-code codehilite"> +<pre><span></span><code><span class="kn">from</span> <span class="nn">pyspark.sql.session</span> <span class="kn">import</span> <span class="n">SparkSession</span> <span class="k">as</span> <span class="n">PySparkSession</span> +<span class="kn">from</span> <span class="nn">sqlglot.dataframe.sql.session</span> <span class="kn">import</span> <span class="n">SparkSession</span> +<span class="kn">from</span> <span class="nn"><a href="dataframe/sql.html">sqlglot.dataframe.sql</a></span> <span class="kn">import</span> <span class="n">types</span> +<span class="kn">from</span> <span class="nn"><a href="dataframe/sql.html">sqlglot.dataframe.sql</a></span> <span class="kn">import</span> <span class="n">functions</span> <span class="k">as</span> <span class="n">F</span> + +<span class="n">data</span> <span class="o">=</span> <span class="p">[</span> + <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="s2">"Jack"</span><span class="p">,</span> <span class="s2">"Shephard"</span><span class="p">,</span> <span class="mi">34</span><span class="p">),</span> + <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="s2">"John"</span><span class="p">,</span> <span class="s2">"Locke"</span><span class="p">,</span> <span class="mi">48</span><span class="p">),</span> + <span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="s2">"Kate"</span><span class="p">,</span> <span class="s2">"Austen"</span><span class="p">,</span> <span class="mi">34</span><span class="p">),</span> + <span class="p">(</span><span class="mi">4</span><span class="p">,</span> <span class="s2">"Claire"</span><span class="p">,</span> <span class="s2">"Littleton"</span><span class="p">,</span> <span class="mi">22</span><span class="p">),</span> + <span class="p">(</span><span class="mi">5</span><span class="p">,</span> <span class="s2">"Hugo"</span><span class="p">,</span> <span class="s2">"Reyes"</span><span class="p">,</span> <span class="mi">26</span><span class="p">),</span> +<span class="p">]</span> +<span class="n">schema</span> <span class="o">=</span> <span class="n">types</span><span class="o">.</span><span class="n">StructType</span><span class="p">([</span> + <span class="n">types</span><span class="o">.</span><span class="n">StructField</span><span class="p">(</span><span class="s1">'employee_id'</span><span class="p">,</span> <span class="n">types</span><span class="o">.</span><span class="n">IntegerType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> + <span class="n">types</span><span class="o">.</span><span class="n">StructField</span><span class="p">(</span><span class="s1">'fname'</span><span class="p">,</span> <span class="n">types</span><span class="o">.</span><span class="n">StringType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> + <span class="n">types</span><span class="o">.</span><span class="n">StructField</span><span class="p">(</span><span class="s1">'lname'</span><span class="p">,</span> <span class="n">types</span><span class="o">.</span><span class="n">StringType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> + <span class="n">types</span><span class="o">.</span><span class="n">StructField</span><span class="p">(</span><span class="s1">'age'</span><span class="p">,</span> <span class="n">types</span><span class="o">.</span><span class="n">IntegerType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> +<span class="p">])</span> + +<span class="n">sql_statements</span> <span class="o">=</span> <span class="p">(</span> + <span class="n">SparkSession</span><span class="p">()</span> + <span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">schema</span><span class="p">)</span> + <span class="o">.</span><span class="n">groupBy</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">col</span><span class="p">(</span><span class="s2">"age"</span><span class="p">))</span> + <span class="o">.</span><span class="n">agg</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">countDistinct</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">col</span><span class="p">(</span><span class="s2">"employee_id"</span><span class="p">))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"num_employees"</span><span class="p">))</span> + <span class="o">.</span><span class="n">sql</span><span class="p">(</span><span class="n">dialect</span><span class="o">=</span><span class="s2">"spark"</span><span class="p">)</span> +<span class="p">)</span> + +<span class="n">pyspark</span> <span class="o">=</span> <span class="n">PySparkSession</span><span class="o">.</span><span class="n">builder</span><span class="o">.</span><span class="n">master</span><span class="p">(</span><span class="s2">"local[*]"</span><span class="p">)</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> + +<span class="n">df</span> <span class="o">=</span> <span class="kc">None</span> +<span class="k">for</span> <span class="n">sql</span> <span class="ow">in</span> <span class="n">sql_statements</span><span class="p">:</span> + <span class="n">df</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">sql</span><span class="p">(</span><span class="n">sql</span><span class="p">)</span> + +<span class="k">assert</span> <span class="n">df</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> +<span class="n">df</span><span class="o">.</span><span class="n">show</span><span class="p">()</span> +</code></pre> +</div> + +<h1 id="unsupportable-operations">Unsupportable Operations</h1> + +<p>Any operation that lacks a way to represent it in SQL cannot be supported by this tool. An example of this would be rdd operations. Since the DataFrame API though is mostly modeled around SQL concepts most operations can be supported.</p> +</div> + + <input id="mod-dataframe-view-source" class="view-source-toggle-state" type="checkbox" aria-hidden="true" tabindex="-1"> + + <label class="view-source-button" for="mod-dataframe-view-source"><span>View Source</span></label> + + <div class="pdoc-code codehilite"><pre><span></span><span id="L-1"><a href="#L-1"><span class="linenos">1</span></a><span class="sd">"""</span> +</span><span id="L-2"><a href="#L-2"><span class="linenos">2</span></a><span class="sd">.. include:: ./README.md</span> +</span><span id="L-3"><a href="#L-3"><span class="linenos">3</span></a><span class="sd">"""</span> +</span></pre></div> + + + </section> + </main> +<script> + function escapeHTML(html) { + return document.createElement('div').appendChild(document.createTextNode(html)).parentNode.innerHTML; + } + + const originalContent = document.querySelector("main.pdoc"); + let currentContent = originalContent; + + function setContent(innerHTML) { + let elem; + if (innerHTML) { + elem = document.createElement("main"); + elem.classList.add("pdoc"); + elem.innerHTML = innerHTML; + } else { + elem = originalContent; + } + if (currentContent !== elem) { + currentContent.replaceWith(elem); + currentContent = elem; + } + } + + function getSearchTerm() { + return (new URL(window.location)).searchParams.get("search"); + } + + const searchBox = document.querySelector(".pdoc input[type=search]"); + searchBox.addEventListener("input", function () { + let url = new URL(window.location); + if (searchBox.value.trim()) { + url.hash = ""; + url.searchParams.set("search", searchBox.value); + } else { + url.searchParams.delete("search"); + } + history.replaceState("", "", url.toString()); + onInput(); + }); + window.addEventListener("popstate", onInput); + + + let search, searchErr; + + async function initialize() { + try { + search = await new Promise((resolve, reject) => { + const script = document.createElement("script"); + script.type = "text/javascript"; + script.async = true; + script.onload = () => resolve(window.pdocSearch); + script.onerror = (e) => reject(e); + script.src = "../search.js"; + document.getElementsByTagName("head")[0].appendChild(script); + }); + } catch (e) { + console.error("Cannot fetch pdoc search index"); + searchErr = "Cannot fetch search index."; + } + onInput(); + + document.querySelector("nav.pdoc").addEventListener("click", e => { + if (e.target.hash) { + searchBox.value = ""; + searchBox.dispatchEvent(new Event("input")); + } + }); + } + + function onInput() { + setContent((() => { + const term = getSearchTerm(); + if (!term) { + return null + } + if (searchErr) { + return `<h3>Error: ${searchErr}</h3>` + } + if (!search) { + return "<h3>Searching...</h3>" + } + + window.scrollTo({top: 0, left: 0, behavior: 'auto'}); + + const results = search(term); + + let html; + if (results.length === 0) { + html = `No search results for '${escapeHTML(term)}'.` + } else { + html = `<h4>${results.length} search result${results.length > 1 ? "s" : ""} for '${escapeHTML(term)}'.</h4>`; + } + for (let result of results.slice(0, 10)) { + let doc = result.doc; + let url = `../${doc.modulename.replaceAll(".", "/")}.html`; + if (doc.qualname) { + url += `#${doc.qualname}`; + } + + let heading; + switch (result.doc.kind) { + case "function": + if (doc.fullname.endsWith(".__init__")) { + heading = `<span class="name">${doc.fullname.replace(/\.__init__$/, "")}</span>${doc.signature}`; + } else { + heading = `<span class="def">${doc.funcdef}</span> <span class="name">${doc.fullname}</span>${doc.signature}`; + } + break; + case "class": + heading = `<span class="def">class</span> <span class="name">${doc.fullname}</span>`; + if (doc.bases) + heading += `<wbr>(<span class="base">${doc.bases}</span>)`; + heading += `:`; + break; + case "variable": + heading = `<span class="name">${doc.fullname}</span>`; + if (doc.annotation) + heading += `<span class="annotation">${doc.annotation}</span>`; + if (doc.default_value) + heading += `<span class="default_value">${doc.default_value}</span>`; + break; + default: + heading = `<span class="name">${doc.fullname}</span>`; + break; + } + html += ` + <section class="search-result"> + <a href="${url}" class="attr ${doc.kind}">${heading}</a> + <div class="docstring">${doc.doc}</div> + </section> + `; + + } + return html; + })()); + } + + if (getSearchTerm()) { + initialize(); + searchBox.value = getSearchTerm(); + onInput(); + } else { + searchBox.addEventListener("focus", initialize, {once: true}); + } + + searchBox.addEventListener("keydown", e => { + if (["ArrowDown", "ArrowUp", "Enter"].includes(e.key)) { + let focused = currentContent.querySelector(".search-result.focused"); + if (!focused) { + currentContent.querySelector(".search-result").classList.add("focused"); + } else if ( + e.key === "ArrowDown" + && focused.nextElementSibling + && focused.nextElementSibling.classList.contains("search-result") + ) { + focused.classList.remove("focused"); + focused.nextElementSibling.classList.add("focused"); + focused.nextElementSibling.scrollIntoView({ + behavior: "smooth", + block: "nearest", + inline: "nearest" + }); + } else if ( + e.key === "ArrowUp" + && focused.previousElementSibling + && focused.previousElementSibling.classList.contains("search-result") + ) { + focused.classList.remove("focused"); + focused.previousElementSibling.classList.add("focused"); + focused.previousElementSibling.scrollIntoView({ + behavior: "smooth", + block: "nearest", + inline: "nearest" + }); + } else if ( + e.key === "Enter" + ) { + focused.querySelector("a").click(); + } + } + }); +</script></body> +</html>
\ No newline at end of file |