Slides
This commit is contained in:
parent
4a666977a5
commit
d0922d87cd
GPG key ID:
3E5F9B3ABD3FDB60
File diff suppressed because one or more lines are too long
Binary file not shown.
|
Before Width: | Height: | Size: 37 KiB After Width: | Height: | Size: 48 KiB |
|
|
@ -14,11 +14,11 @@
|
|||
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no, minimal-ui">
|
||||
|
||||
<link rel="stylesheet" href="../reveal.js-3.5.0/css/reveal.css">
|
||||
<link rel="stylesheet" href="../../reveal.js-3.7.0/css/reveal.css">
|
||||
<link rel="stylesheet" href="ubodin.css" id="theme">
|
||||
|
||||
<!-- Code syntax highlighting -->
|
||||
<link rel="stylesheet" href="../reveal.js-3.5.0/lib/css/zenburn.css">
|
||||
<link rel="stylesheet" href="../../reveal.js-3.7.0/lib/css/zenburn.css">
|
||||
|
||||
|
||||
<style type="text/css">
|
||||
|
|
@ -35,7 +35,7 @@
|
|||
var link = document.createElement( 'link' );
|
||||
link.rel = 'stylesheet';
|
||||
link.type = 'text/css';
|
||||
link.href = window.location.search.match( /print-pdf/gi ) ? '../reveal.js-3.5.0/css/print/pdf.css' : '../reveal.js-3.5.0/css/print/paper.css';
|
||||
link.href = window.location.search.match( /print-pdf/gi ) ? '../../reveal.js-3.7.0/css/print/pdf.css' : '../reveal.js-3.7.0/css/print/paper.css';
|
||||
document.getElementsByTagName( 'head' )[0].appendChild( link );
|
||||
</script>
|
||||
|
||||
|
|
@ -116,6 +116,7 @@
|
|||
<tr><td>1575731228</td><td>1</td></tr>
|
||||
<tr><td>1575731237</td><td>1</td></tr>
|
||||
</table>
|
||||
<p class="fragment">Step 1: Line up the readings</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
|
|
@ -149,7 +150,7 @@
|
|||
</section>
|
||||
|
||||
<section>
|
||||
<pre><code>
|
||||
<pre><code class="sql">
|
||||
INSERT INTO series_one_buckets
|
||||
SELECT CAST(time / 10 AS int) AS bucket,
|
||||
FIRST(reading)
|
||||
|
|
@ -158,7 +159,7 @@
|
|||
</code></pre>
|
||||
<p class="fragment">Interpolate missing values</p>
|
||||
<p class="fragment">Hand tune around the switchover as-needed</p>
|
||||
<pre class="fragment"><code>
|
||||
<pre class="fragment"><code class="sql">
|
||||
SELECT a.time, a.reading AS reading_one
|
||||
b.reading AS reading_two
|
||||
FROM series_one_buckets a, series_two_buckets b
|
||||
|
|
@ -201,7 +202,8 @@
|
|||
|
||||
<section>
|
||||
<section>
|
||||
<p>Carol gets a dataset from Dave</p>
|
||||
<h3>Act 2</h3>
|
||||
<p class="fragment">Carol gets a dataset from Dave</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
|
|
@ -301,10 +303,7 @@
|
|||
-->
|
||||
<section>
|
||||
<p>Data science is <span style="color: lightgrey;">nuanced</span>.</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<p>Assumptions can't be avoided!</p>
|
||||
<p class="fragment">Assumptions can't be avoided!</p>
|
||||
<p class="fragment">It's easy to miss an assumption when re-using work.</p>
|
||||
</section>
|
||||
|
||||
|
|
@ -312,16 +311,20 @@
|
|||
<img src="graphics/montoya.jpeg" height="400px" />
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<h3>There needs to be a better way!</h3>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<p>Annotate data with warnings.</p>
|
||||
|
||||
<p class="fragment" data-fragment-index="1">If you use this value/record, be warned!</p>
|
||||
<p class="fragment" data-fragment-index="1">If you use this value/record, <br/>here's what you need to know!</p>
|
||||
|
||||
<h3 class="fragment" data-fragment-index="2">Caveat Physicus</h3>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<p>Apply a caveat when volating an assumption might...</p>
|
||||
<p>Declare a caveat when volating an assumption might...</p>
|
||||
<ul>
|
||||
<li class="fragment">... change one or more values</li>
|
||||
<li class="fragment">... remove one or more records</li>
|
||||
|
|
@ -333,7 +336,9 @@
|
|||
|
||||
<section>
|
||||
<section>
|
||||
<p>A brief digression...</p>
|
||||
<p>So what is a caveat?</p>
|
||||
|
||||
<p class="fragment">A brief digression...</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
|
|
@ -355,23 +360,23 @@
|
|||
<section>
|
||||
<p class="fragment"><b>Possible</b> tuples exist in at least one one possible world. $$possible(\mathcal R) = \bigcup_{R \in \mathcal R} R$$</p>
|
||||
<p class="fragment"><b>Certain</b> tuples exist in all possible worlds. $$certain(\mathcal R) = \bigcap_{R \in \mathcal R} R$$</p>
|
||||
<p style="font-size: 70%;" class="fragment">(with generalizations beyond set semantics)</p>
|
||||
<p style="font-size: 70%;" class="fragment">(not limited to set semantics)</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<pre><code>
|
||||
<pre><code class="sql">
|
||||
SELECT setting_1, setting_2,
|
||||
caveat(estimate, 'Only correct if phi is 42')
|
||||
AS estimate
|
||||
FROM Simulation;
|
||||
</code></pre>
|
||||
is the same as
|
||||
<pre><code>
|
||||
<pre><code class="sql">
|
||||
SELECT setting_1, setting_2, estimate
|
||||
FROM Simulation;
|
||||
</code></pre>
|
||||
<p class="fragment"><b>Caveat: </b>If it turns out that phi ≠ 42, <br/>all estimate values might be wrong.</p>
|
||||
<p style="font-size: 70%" class="fragment">(The query annotates all <span style="font-family: monospace;">`estimate`</span> values with the caveat)</p>
|
||||
<p class="fragment"><b>Caveat: </b>If it turns out that phi ≠ 42, <br/>all <span style="font-family: monospace;">estimate</span> values could be wrong.</p>
|
||||
<p style="font-size: 70%" class="fragment">(The first query annotates all <span style="font-family: monospace;">`estimate`</span> values with the caveat)</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
|
|
@ -391,56 +396,45 @@
|
|||
</section>
|
||||
|
||||
<section>
|
||||
<h3>Why?</h3>
|
||||
<p>Caveats...</p>
|
||||
<dl>
|
||||
<div class="fragment">
|
||||
<dt>... go where the data goes</dt>
|
||||
<dd>Automatic propagation to derived values.</dd>
|
||||
</div>
|
||||
|
||||
<div class="fragment">
|
||||
<dt>... stop where the data stops</dt>
|
||||
<dd>Irrelevant caveats don't get propagated</dd>
|
||||
</div>
|
||||
</dl>
|
||||
<h3>Applying Caveats</h3>
|
||||
<p class="fragment">a few examples...</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<p>a few examples...</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<pre><code>
|
||||
SELECT bucket,
|
||||
CASE WHEN bucket_size > 1 THEN
|
||||
caveat(reading, 'a reading got offset')
|
||||
ELSE reading END AS reading
|
||||
FROM (
|
||||
SELECT CAST(time / 10 AS int) AS bucket,
|
||||
FIRST(reading) AS reading
|
||||
COUNT(*) AS bucket_size
|
||||
FROM sensor
|
||||
)
|
||||
<p>Mark multi-valued buckets <span class="fragment">(key repair).</span></p>
|
||||
<pre><code class="sql" data-line-numbers="2-3">
|
||||
SELECT bucket,
|
||||
CASE WHEN bucket_size > 1 THEN
|
||||
caveat(reading, 'Picked between two bucket values.')
|
||||
ELSE reading END AS reading
|
||||
FROM (
|
||||
SELECT CAST(time / 10 AS int) AS bucket,
|
||||
FIRST(reading) AS reading
|
||||
COUNT(*) AS bucket_size
|
||||
FROM sensor
|
||||
)
|
||||
</code></pre>
|
||||
<p class="fragment">interpolation is more complex... but similar</p>
|
||||
<p class="fragment">Interpolation is more complex... but similar.</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<pre><code>
|
||||
CASE WHEN race_ethnicity
|
||||
IN ('white non-hispanic', 'black non-hispanic', /* ... */)
|
||||
THEN race_ethnicity
|
||||
ELSE caveat(race_ethnicity,
|
||||
'Unexpected race_ethnicity: ' & race_ethnicity)
|
||||
END
|
||||
<p>Mark unexpected values the model wasn't trained on.</p>
|
||||
<pre><code class="sql">
|
||||
SELECT
|
||||
CASE WHEN race_ethnicity
|
||||
IN ('white non-hispanic', 'black non-hispanic', /* ... */)
|
||||
THEN race_ethnicity
|
||||
ELSE caveat(race_ethnicity,
|
||||
'Unexpected race_ethnicity: ' & race_ethnicity)
|
||||
END, /* ... */
|
||||
FROM R
|
||||
</code></pre>
|
||||
<p class="fragment">we can automate checks like this</p>
|
||||
<p class="fragment">This check can be automated.</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<p>Spark's CSV loader can augment tables with a $\texttt{parse_error}$ column.</p>
|
||||
<pre><code>
|
||||
<pre><code class="sql">
|
||||
SELECT * FROM csv_file
|
||||
WHERE
|
||||
CASE WHEN parse_error IS NULL THEN TRUE ELSE
|
||||
|
|
@ -449,6 +443,26 @@
|
|||
</code></pre>
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h3>Why?</h3>
|
||||
<h4 class="fragment" data-fragment-index="1">Propagation</h4>
|
||||
<dl>
|
||||
<dd class="fragment" data-fragment-index="2" style="margin-left: -20px;">Caveats...</dd>
|
||||
|
||||
<div class="fragment" data-fragment-index="2">
|
||||
<dt>... can go where the data goes</dt>
|
||||
<dd>Derived values retain caveats on source data.</dd>
|
||||
</div>
|
||||
|
||||
<div class="fragment" data-fragment-index="3">
|
||||
<dt>... stop where the data stops</dt>
|
||||
<dd>Irrelevant caveats don't get propagated</dd>
|
||||
</div>
|
||||
</dl>
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h3>Caveats</h3>
|
||||
|
||||
|
|
@ -462,55 +476,61 @@
|
|||
|
||||
<section>
|
||||
<section>
|
||||
Another brief digression...
|
||||
<h3>How are caveats propagated?</h3>
|
||||
<p class="fragment">Another brief digression...</p>
|
||||
</section>
|
||||
<section>
|
||||
<h3>Value Annotations</h3>
|
||||
|
||||
<p style="margin-top: 50px; font-size: 70%;">
|
||||
<b>MONDRIAN: Annotating and Querying Databases through Colors and Blocks.</b><br/>
|
||||
Floris Geerts, Anastasios Kementsietsidis, Diego Milano
|
||||
</p>
|
||||
<p style="margin-top: 50px; font-size: 70%;">
|
||||
<p style="margin-top: 50px; font-size: 70%;" class="fragment" data-fragment-index="1">
|
||||
<b>Provenance in Databases: Why, How, and <u>Where</u></b><br/>
|
||||
James Cheney, Laura Chiticariu and Wang-Chiew Tan
|
||||
</p>
|
||||
|
||||
<p>and more...</p>
|
||||
<p style="margin-top: 50px; font-size: 70%;" class="fragment" data-fragment-index="2">
|
||||
<b>MONDRIAN: Annotating and Querying Databases through Colors and Blocks.</b><br/>
|
||||
Floris Geerts, Anastasios Kementsietsidis, Diego Milano
|
||||
</p>
|
||||
|
||||
<p class="fragment" data-fragment-index="2">and more...</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<h3>Value Annotations</h3>
|
||||
<pre><code>
|
||||
<pre><code class="sql">
|
||||
CREATE VIEW Q AS
|
||||
SELECT R.A, R.B+R.C AS B FROM R
|
||||
SELECT R.A AS X,
|
||||
R.B+R.C AS Y
|
||||
FROM R
|
||||
</code></pre>
|
||||
<p class="fragment" style="font-size: 70%">
|
||||
$$annot(\texttt{Q.A}, i) \leftarrow annot(\texttt{R.A}, i)$$
|
||||
$$annot(\texttt{Q.X}[i]) \leftarrow annot(\texttt{R.A}[i])$$
|
||||
</p>
|
||||
<p class="fragment" style="font-size: 70%">
|
||||
$$annot(\texttt{Q.B}, i) \leftarrow annot(\texttt{R.B}, i) \cup annot(\texttt{R.C}, i)$$
|
||||
$$annot(\texttt{Q.Y}[i]) \leftarrow annot(\texttt{R.B}[i]) \cup annot(\texttt{R.C}[i])$$
|
||||
</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<h3>Value Annotations</h3>
|
||||
<pre><code>
|
||||
<pre><code class="sql">
|
||||
CREATE VIEW Q AS
|
||||
SELECT R.A, SUM(R.B) AS B FROM R
|
||||
SELECT R.A AS X,
|
||||
SUM(R.B) AS Y
|
||||
FROM R
|
||||
</code></pre>
|
||||
<p class="fragment" style="font-size: 70%">
|
||||
$$annot(\texttt{Q.A}, i) \leftarrow \bigcup_{j\;:\;\texttt{R.A}[j] = Q.A[i]} annot(\texttt{R.A}, j)$$
|
||||
$$annot(\texttt{Q.X}[i]) \leftarrow \bigcup_{j\;:\;\texttt{R.A}[j] = Q.A[i]} annot(\texttt{R.A}[j])$$
|
||||
</p>
|
||||
<p class="fragment" style="font-size: 70%">
|
||||
$$annot(\texttt{Q.B}, i) \leftarrow \bigcup_{j\;:\;\texttt{R.B}[j] = Q.B[i]} annot(\texttt{R.B}, j)$$
|
||||
$$annot(\texttt{Q.Y}[i]) \leftarrow \bigcup_{j\;:\;\texttt{R.B}[j] = Q.B[i]} annot(\texttt{R.B}[j])$$
|
||||
</p>
|
||||
<p class="fragment">... not the semantics we want</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<p>
|
||||
If $\texttt{R.A}$ is wrong, any $\texttt{Q.B}$ could change.
|
||||
Caveats on $\texttt{R.A}$ also affect $\texttt{Q.B}$.
|
||||
</p>
|
||||
</section>
|
||||
|
||||
|
|
@ -549,13 +569,19 @@
|
|||
</section>
|
||||
|
||||
<section>
|
||||
<p><b>Certain Data Elements: </b> Elements guaranteed to be in the result as-is <u>in all possible worlds</u>.</p>
|
||||
<p><b>Certain Data Elements: </b> Elements guaranteed to be in the result <u>in all possible worlds</u>.</p>
|
||||
|
||||
<p class="fragment">... i.e., elements unaffected by the choice of possible world.</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<p>If a caveatted element can't affect an output element, don't propagate its caveats!</p>
|
||||
<p class="fragment">Propagate caveats to any data elements that could be affected by a change.</p>
|
||||
<p class="fragment"><b>Problem: </b> This is expensive!</p>
|
||||
</section>
|
||||
<section>
|
||||
<p><b>Challenge: </b> How do we propagate caveats<br/>without penalizing query evaluation.</p>
|
||||
|
||||
<p class="fragment">Don't!</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
|
|
@ -596,31 +622,135 @@
|
|||
<section>
|
||||
<h3>Instrumenting Queries</h3>
|
||||
<p class="fragment">≅ computing certain answers! (CoNP-Complete)</p>
|
||||
<p class="fragment">Need an approximation</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<h3>Conservative Approximation</h3>
|
||||
|
||||
<div class="fragment">
|
||||
<div class="fragment" data-fragment-index="1">
|
||||
<p style="margin-top: 20px; font-size: 60%;">
|
||||
<b>Correctness of SQL Queries on Databases with Nulls.</b><br/>
|
||||
Paolo Guagliardo, Leonid Libkin
|
||||
</p>
|
||||
<p style="margin-top: 20px; font-size: 60%;">
|
||||
<p style="margin-top: 20px; font-size: 60%;" class="fragment highlight-blue grow" data-fragment-index="4">
|
||||
<b>Uncertainty Annotated Databases - A Lightweight Approach for Approximating Certain Answers</b><br/>
|
||||
Su Feng, Aaron Huber, Boris Glavic, Oliver Kennedy
|
||||
</p>
|
||||
</div>
|
||||
<ul>
|
||||
<li class="fragment">Unmarked rows are guaranteed to be caveat-free.</li>
|
||||
<li class="fragment">Marked rows might not be caveatted.</li>
|
||||
<li class="fragment" data-fragment-index="2">Unmarked rows are guaranteed to be caveat-free.</li>
|
||||
<li class="fragment" data-fragment-index="3">Marked rows might not be caveatted.</li>
|
||||
</ul>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<p>Ongoing effort to formalize propagation for values.</p>
|
||||
<p><b>Work with Boris Glavic + Su Feng @ IIT</b></p>
|
||||
<p>Add and maintain a binary "has caveat"<br/>column for each row/column.</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<pre><code class="sql">
|
||||
CREATE VIEW by_language AS
|
||||
SELECT language,
|
||||
CASE WHEN CAST(salary AS float) IS NOT NULL THEN
|
||||
|
||||
caveat(NULL, 'Could not cast [ '&salary&' ] to float.')
|
||||
|
||||
ELSE CAST(salary AS float) END AS salary
|
||||
FROM raw_csv_data;
|
||||
</code></pre>
|
||||
<div class="fragment">
|
||||
becomes
|
||||
<pre><code class="sql">
|
||||
CREATE VIEW by_language AS
|
||||
SELECT language, CAST(salary AS float) AS salary,
|
||||
FALSE AS _caveat_field_language,
|
||||
CAST(salary as float) IS NULL AS _caveat_field_salary
|
||||
FALSE AS _caveat_row
|
||||
FROM raw_csv_data;
|
||||
</code></pre>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<pre><code class="sql">
|
||||
SELECT salary
|
||||
FROM by_language
|
||||
WHERE language = 'Scala'
|
||||
</code></pre>
|
||||
<div class="fragment">
|
||||
becomes
|
||||
<pre><code class="sql">
|
||||
SELECT salary,
|
||||
_caveat_field_salary AS _caveat_field_salary,
|
||||
_caveat_row AND _caveat_field_language AS _caveat_row
|
||||
FROM by_language
|
||||
WHERE language = 'Scala'
|
||||
</code></pre>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<pre><code class="sql">
|
||||
SELECT AVG(salary) AS salary
|
||||
FROM by_language
|
||||
</code></pre>
|
||||
<div class="fragment">
|
||||
becomes
|
||||
<pre><code class="sql">
|
||||
SELECT salary,
|
||||
GROUP_OR(_caveat_field_salary) AS _caveat_field_salary,
|
||||
FALSE AS _caveat_row
|
||||
FROM by_language
|
||||
</code></pre>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<pre><code class="sql">
|
||||
SELECT language, AVG(salary) AS salary
|
||||
FROM by_language
|
||||
GROUP BY language
|
||||
</code></pre>
|
||||
<div class="fragment">
|
||||
... first we evaluate
|
||||
<pre><code class="sql">
|
||||
SELECT GROUP_OR(_caveat_field_language)
|
||||
FROM by_language
|
||||
</code></pre>
|
||||
</div>
|
||||
<p class="fragment">Can often be evaluated statically.</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<h3>If TRUE</h3>
|
||||
|
||||
<pre><code class="sql">
|
||||
SELECT language, AVG(salary) AS salary
|
||||
FALSE AS _caveat_field_language
|
||||
TRUE AS _caveat_field_salary
|
||||
GROUP_AND(_caveat_field_language OR
|
||||
_caveat_row) AS _caveat_row
|
||||
FROM by_language
|
||||
GROUP BY language
|
||||
</code></pre>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<h3>If FALSE</h3>
|
||||
|
||||
<pre><code class="sql">
|
||||
SELECT language, AVG(salary) AS salary
|
||||
FALSE AS _caveat_field_language
|
||||
GROUP_OR(_caveat_field_salary,
|
||||
_caveat_row) AS _caveat_field_salary
|
||||
GROUP_AND(_caveat_row) AS _caveat_row
|
||||
FROM by_language
|
||||
GROUP BY language
|
||||
</code></pre>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<p>Ongoing work with Boris Glavic + Su Feng @ IIT</p>
|
||||
</section>
|
||||
|
||||
</section>
|
||||
|
|
@ -651,14 +781,14 @@
|
|||
<section>
|
||||
<h3>Program Slicing</h3>
|
||||
|
||||
<p>Eliminate lines of code not relevant to computing a specific value.</p>
|
||||
<p>Eliminate lines of code not relevant<br/>to computing a specific value.</p>
|
||||
|
||||
<p class="fragment">This is <i>exactly</i> what a database optimizer does.</p>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<p><b>Lookup: </b> Caveats on $\texttt{R.A}[i]$</p>
|
||||
<pre class="fragment"><code>
|
||||
<pre class="fragment"><code class="sql">
|
||||
SELECT A
|
||||
FROM R
|
||||
WHERE ROWID = i
|
||||
|
|
@ -676,17 +806,17 @@
|
|||
|
||||
<section>
|
||||
<h3>Isolate the message</h3>
|
||||
<pre><code>
|
||||
WITH data_source AS
|
||||
SELECT caveat(A, 'only valid '& B &' is within tolerances.') AS A,
|
||||
C, D, E
|
||||
FROM R
|
||||
|
||||
SELECT C, D, E FROM data_source
|
||||
<pre><code class="sql">
|
||||
WITH data_source AS
|
||||
SELECT caveat(A, 'valid if '& B &' is within tolerances.') AS A,
|
||||
C, D, E
|
||||
FROM R
|
||||
|
||||
SELECT C, D, E FROM data_source
|
||||
</code></pre>
|
||||
<p>becomes</p>
|
||||
<pre><code>
|
||||
SELECT 'only valid '& B &' is within tolerances.'
|
||||
<pre><code class="sql">
|
||||
SELECT 'valid if '& B &' is within tolerances.'
|
||||
AS caveat_message
|
||||
FROM R
|
||||
</code></pre>
|
||||
|
|
@ -828,11 +958,11 @@
|
|||
</section>
|
||||
|
||||
<section>
|
||||
<pre><code>
|
||||
<pre><code class="sql">
|
||||
UPDATE R SET A = 'foo' WHERE ROWID = 3;
|
||||
</code></pre>
|
||||
becomes
|
||||
<pre><code>
|
||||
<pre><code class="sql">
|
||||
SELECT CASE ROWID
|
||||
WHEN 3 THEN 'foo'
|
||||
ELSE A END AS A,
|
||||
|
|
@ -842,11 +972,11 @@
|
|||
</section>
|
||||
|
||||
<section>
|
||||
<pre><code>
|
||||
<pre><code class="sql">
|
||||
INSERT INTO R() VALUES ();
|
||||
</code></pre>
|
||||
becomes
|
||||
<pre><code>
|
||||
<pre><code class="sql">
|
||||
SELECT * FROM R
|
||||
UNION ALL
|
||||
SELECT NULL AS A, NULL AS B,
|
||||
|
|
@ -855,11 +985,11 @@
|
|||
</section>
|
||||
|
||||
<section>
|
||||
<pre><code>
|
||||
<pre><code class="sql">
|
||||
ALTER R ADD COLUMN `bar`;
|
||||
</code></pre>
|
||||
becomes
|
||||
<pre><code>
|
||||
<pre><code class="sql">
|
||||
SELECT *, NULL as `bar` FROM R;
|
||||
</code></pre>
|
||||
</section>
|
||||
|
|
@ -913,7 +1043,7 @@
|
|||
<img src="graphics/vizier-blue.svg" height="100px" style="vertical-align: middle; margin-right: 20px;" />
|
||||
<span style="vertical-align: middle;" ><a href="https://vizierdb.info/">https://vizierdb.info</a></span>
|
||||
</h3>
|
||||
<pre style="margin-top: 50px;"><code>
|
||||
<pre style="margin-top: 50px;"><code class="sql">
|
||||
$> pip3 install --user vizier-webapi
|
||||
$> vizier
|
||||
</code></pre>
|
||||
|
|
@ -1060,7 +1190,9 @@
|
|||
},
|
||||
{ src: '../reveal.js-3.5.0/plugin/markdown/marked.js', condition: function() { return !!document.querySelector( '[data-markdown]' ); } },
|
||||
{ src: '../reveal.js-3.5.0/plugin/markdown/markdown.js', condition: function() { return !!document.querySelector( '[data-markdown]' ); } },
|
||||
{ src: '../reveal.js-3.5.0/plugin/highlight/highlight.js', async: true, condition: function() { return !!document.querySelector( 'tt code' ); }, callback: function() { hljs.initHighlightingOnLoad(); } },
|
||||
//{ src: '../reveal.js-3.5.0/plugin/highlight/highlight.js', async: true, condition: function() { return !!document.querySelector( 'tt code' ); }, callback: function() { hljs.initHighlightingOnLoad(); } },
|
||||
{ src: '../../reveal.js-3.7.0/plugin/highlight/highlight-9.16.2.js', async: true,
|
||||
callback: function() { hljs.initHighlightingOnLoad(); } },
|
||||
{ src: '../reveal.js-3.5.0/plugin/zoom-js/zoom.js', async: true },
|
||||
{ src: '../reveal.js-3.5.0/plugin/notes/notes.js', async: true }
|
||||
]
|
||||
|
|
|
|||
15
slides/talks/2019-5-VizierCaveats/notes.txt
Normal file
15
slides/talks/2019-5-VizierCaveats/notes.txt
Normal file
|
|
@ -0,0 +1,15 @@
|
|||
--- Salary ---
|
||||
|
||||
1n9lRY5NxHjmXfqZfXJxytBqznzP_vWOPfSbv2rL-T38/Form Responses 1
|
||||
|
||||
--- by_language ---
|
||||
|
||||
SELECT PRIMARY_LANGUAGE_TECHNOLOGY_STACK AS LANGUAGE, COUNT(*) as tot,
|
||||
AVG(HOW_MANY_YEARS_HAVE_YOU_WORKED_IN_TECH) as YEARSWORKED,
|
||||
MIN(HOW_MANY_YEARS_HAVE_YOU_WORKED_IN_TECH) as yearsworked_min,
|
||||
MAX(HOW_MANY_YEARS_HAVE_YOU_WORKED_IN_TECH) as yearsworked_max,
|
||||
AVG(WHAT_IS_YOUR_ANNUALIZED_BASE_SALARY_IN_USD) as salary
|
||||
FROM salaries
|
||||
GROUP BY PRIMARY_LANGUAGE_TECHNOLOGY_STACK
|
||||
HAVING tot > 2;
|
||||
|
||||
Loading…
Reference in a new issue