ttu
/
CaReCur
mirror of https://github.com/thomastu/CaReCur


  
1

	
2

	
3

	
4

	
5

	
6

	
7

	
8

	
9

	
10

	
11

	
12

	
13

	
14

	
15

	
16

	
17

	
18

	
19

	
20

	
21

	
22

	
23

	
24

	
25

	
26

	
27

	
28

	
29

	
30

	
31

	
32

	
33

	
34

	
35

	
36

	
37

	
38

	
39

	
40

	
41

	
42

	
43

	
44

	
45

	
46

	
47

	
48

	
49

	
50

	
51

	
52

	
53

	
54

	
55

	
56

	
57

	
58

	
59

	
60

	
61

	
62

	
63

	
64

	
65

	
66

	
67

	
68

	
69

	
70

	
71

	
72

	
73

	
74

	
75

	
76

	
77

	
78

	
79

	
80

	
81

	
82

	
83

	
84

	
85

	
86

	
87

	
88

	
89

	
90

	
91

	
92

	
93

	
94

	
95

	
96

	
97

	
98

	
99

	
100

	
101

	
102

	
103

	
104

	
105

	
106

	
107

	
108

	
109

	
110

	
111

	
112

	
113

	
114

	
115

	
116

	
117

	
118

	
119

	
120

	
121

	
122

	
123

	
124

	
125

	
126

	
127

	
128

	
129

	
130

	
131

	
132

	
133

	
134

	
135

	
136

	
137

	
138

	
139

	
140

	
141

	
142

	
143

	
144

	
145

	
146

	
147

	
148

	
149

	
150

	
151

	
152

	
153

	
154

	
155

	
156

	
157

	
158

	
159

	
160

	
161

	
162

	
163

	
164

	
165

	
166

	
167

	
168

	
169

	
170

	
171

	
172

	
173

	
174

	
175

	
176

	
177

	
178

	
179

	
180

	
181

	
182

	
183

	
184

	
185

	
186

	
187

	
188

	
189

	
190

	
191

	
192

	
193

	
194

	
195

	
196

	
197

	
198

	
199

	
200

	
201

	
202

	
203

	
204

	
205

	
206

	
207

	
208

	
209

	
210

	
211

	
212

	
213

	
214

	
215

	
216

	
217

	
218

	
219

	
220

	
221

	
222

	
223

	
224

	
225

	
226

	
227

	
228

	
229

	
230

	
231

	
232

	
233

	
234

	
235

	
236

	
237

	
238

	
239

	
240

	
241

	
242

	
243

	
244

	
245

	
246

	
247

	
248

	
249

	
250

	
251

	
252

	
253

	
254

	
255

	
256

	
257

	
258

	
259

	
260

	
261

	
262

	
263

	
264

	
265

	
266

	
267

	
268

	
269

	
270

	
271

	
272

	
273

	
274

	
275

	
276

	
277

	
278

	
279

	
280

	
281

	
282

	
283

	
284

	
285

	
286

	
287

	
288

	
289

	
290

	
291

	
292

	
293

	
294

	
295

	
296

	
297

	
298

	
299

	
300

	
301

	
302

	
303

	
304

	
305

	
306

	
307

	
308

	
309

	
310

	
311

	
312

	
313

	
314

	
315

	
316

	
317

	
318

	
319

	
320

	
321

	
322

	
323

	
324

	
325

	
326

	
327

	
328

	
329

	
330

	
331

	
332

	
333

	
334

	
335

	
336

	
337

	
338

	
339

	
340

	
341

	
342

	
343

	
344

	
345

	
346

	
347

	
348

	
349

	
350

	
351

	
352

	
353

	
354

	
355

	
356

	
357

	
358

	
359

	
360

	
361

	
362

	
363

	
364

	
365

	
366

	
367

	
368

	
369

	
370

	
371

	
372

	
373

	
374

	
375

	
376

	
377

	
378

	
379

	
380

	
381

	
382

	
383

	
384

	
385

	
386

	
387

	
388

	
389

	
390

	
391

	
392

	
393

	
394

	
395

	
396

	
397

	
398

	
399

	
400

	
401

	
402

	
403

	
404

	
405

	
406

	
407

	
408

	
409

	
410

	
411

	
412

	
413

	
414

	
415

	
416

	
417

	
418

	
419

	
420

	
421

	
422

	
423

	
424

	
425

	
426

	
427

	
428

	
429

	
430

	
431

	
432

	
433

	
434

	
435

	
436

	
437

	
438

	
439

	
440

	
441

	
442

	
443

	
444

	
445

	
446

	
447

	
448

	
449

	
450

	
451

	
452

	
453

	
454

	
455

	
456

	
457

	
458

	
459

	
460

	
461

	
462

	
463

	
464

	
465

	
466

	
467

	
468

	
469

	
470

	
471

	
472

	
473

	
474

	
475

	
476

	
477

	
478

	
479

	
480

	
481

	
482

	
483

	
484

	
485

	
486

	
487

	
488

	
489

	
490

	
491

	
492

	
493

	
494

	
495

	
496

	
497

	
498

	
499

	
500

	
501

	
502

	
503

	
504

	
505

	
506

	
507

	
508

	
509

	
510

	
511

	
512

	
513

	
514

	
515

	
516

	
517

	
518

	
519

	
520

	
521

	
522

	
523

	
524

	
525

	
526

	
527

	
528

	
529

	
530

	
531

	
532

	
533

	
534

	
535

	
536

	
537

	
<!DOCTYPE html>

<html xmlns="http://www.w3.org/1999/xhtml">
  <head>
    <meta charset="utf-8" />
    <title>&lt;no title&gt; &#8212; California Renewable Curtailments  documentation</title>
    <link rel="stylesheet" href="../_static/haiku.css" type="text/css" />
    <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
    <link rel="stylesheet" type="text/css" href="../_static/graphviz.css" />
    <script id="documentation_options" data-url_root="../" src="../_static/documentation_options.js"></script>
    <script src="../_static/jquery.js"></script>
    <script src="../_static/underscore.js"></script>
    <script src="../_static/doctools.js"></script>
    <script src="../_static/language_data.js"></script>
    <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
    <script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
    <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script>
    <link rel="index" title="Index" href="../genindex.html" />
    <link rel="search" title="Search" href="../search.html" /> 
  </head><body>
      <div class="header" role="banner"><h1 class="heading"><a href="../index.html">
          <span>California Renewable Curtailments  documentation</span></a></h1>
        <h2 class="heading"><span>&lt;no title&gt;</span></h2>
      </div>
      <div class="topnav" role="navigation" aria-label="top navigation">
      
        <p>
        <a class="uplink" href="../index.html">Contents</a>
        </p>

      </div>
      <div class="content" role="main">
        
        
<style>
/* CSS for nbsphinx extension */

/* remove conflicting styling from Sphinx themes */
div.nbinput.container,
div.nbinput.container div.prompt,
div.nbinput.container div.input_area,
div.nbinput.container div[class*=highlight],
div.nbinput.container div[class*=highlight] pre,
div.nboutput.container,
div.nboutput.container div.prompt,
div.nboutput.container div.output_area,
div.nboutput.container div[class*=highlight],
div.nboutput.container div[class*=highlight] pre {
    background: none;
    border: none;
    padding: 0 0;
    margin: 0;
    box-shadow: none;
}

/* avoid gaps between output lines */
div.nboutput.container div[class*=highlight] pre {
    line-height: normal;
}

/* input/output containers */
div.nbinput.container,
div.nboutput.container {
    display: -webkit-flex;
    display: flex;
    align-items: flex-start;
    margin: 0;
    width: 100%;
}
@media (max-width: 540px) {
    div.nbinput.container,
    div.nboutput.container {
        flex-direction: column;
    }
}

/* input container */
div.nbinput.container {
    padding-top: 5px;
}

/* last container */
div.nblast.container {
    padding-bottom: 5px;
}

/* input prompt */
div.nbinput.container div.prompt pre {
    color: #307FC1;
}

/* output prompt */
div.nboutput.container div.prompt pre {
    color: #BF5B3D;
}

/* all prompts */
div.nbinput.container div.prompt,
div.nboutput.container div.prompt {
    width: 4.5ex;
    padding-top: 5px;
    position: relative;
    user-select: none;
}

div.nbinput.container div.prompt > div,
div.nboutput.container div.prompt > div {
    position: absolute;
    right: 0;
    margin-right: 0.3ex;
}

@media (max-width: 540px) {
    div.nbinput.container div.prompt,
    div.nboutput.container div.prompt {
        width: unset;
        text-align: left;
        padding: 0.4em;
    }
    div.nboutput.container div.prompt.empty {
        padding: 0;
    }

    div.nbinput.container div.prompt > div,
    div.nboutput.container div.prompt > div {
        position: unset;
    }
}

/* disable scrollbars on prompts */
div.nbinput.container div.prompt pre,
div.nboutput.container div.prompt pre {
    overflow: hidden;
}

/* input/output area */
div.nbinput.container div.input_area,
div.nboutput.container div.output_area {
    -webkit-flex: 1;
    flex: 1;
    overflow: auto;
}
@media (max-width: 540px) {
    div.nbinput.container div.input_area,
    div.nboutput.container div.output_area {
        width: 100%;
    }
}

/* input area */
div.nbinput.container div.input_area {
    border: 1px solid #e0e0e0;
    border-radius: 2px;
    background: #f5f5f5;
}

/* override MathJax center alignment in output cells */
div.nboutput.container div[class*=MathJax] {
    text-align: left !important;
}

/* override sphinx.ext.imgmath center alignment in output cells */
div.nboutput.container div.math p {
    text-align: left;
}

/* standard error */
div.nboutput.container div.output_area.stderr {
    background: #fdd;
}

/* ANSI colors */
.ansi-black-fg { color: #3E424D; }
.ansi-black-bg { background-color: #3E424D; }
.ansi-black-intense-fg { color: #282C36; }
.ansi-black-intense-bg { background-color: #282C36; }
.ansi-red-fg { color: #E75C58; }
.ansi-red-bg { background-color: #E75C58; }
.ansi-red-intense-fg { color: #B22B31; }
.ansi-red-intense-bg { background-color: #B22B31; }
.ansi-green-fg { color: #00A250; }
.ansi-green-bg { background-color: #00A250; }
.ansi-green-intense-fg { color: #007427; }
.ansi-green-intense-bg { background-color: #007427; }
.ansi-yellow-fg { color: #DDB62B; }
.ansi-yellow-bg { background-color: #DDB62B; }
.ansi-yellow-intense-fg { color: #B27D12; }
.ansi-yellow-intense-bg { background-color: #B27D12; }
.ansi-blue-fg { color: #208FFB; }
.ansi-blue-bg { background-color: #208FFB; }
.ansi-blue-intense-fg { color: #0065CA; }
.ansi-blue-intense-bg { background-color: #0065CA; }
.ansi-magenta-fg { color: #D160C4; }
.ansi-magenta-bg { background-color: #D160C4; }
.ansi-magenta-intense-fg { color: #A03196; }
.ansi-magenta-intense-bg { background-color: #A03196; }
.ansi-cyan-fg { color: #60C6C8; }
.ansi-cyan-bg { background-color: #60C6C8; }
.ansi-cyan-intense-fg { color: #258F8F; }
.ansi-cyan-intense-bg { background-color: #258F8F; }
.ansi-white-fg { color: #C5C1B4; }
.ansi-white-bg { background-color: #C5C1B4; }
.ansi-white-intense-fg { color: #A1A6B2; }
.ansi-white-intense-bg { background-color: #A1A6B2; }

.ansi-default-inverse-fg { color: #FFFFFF; }
.ansi-default-inverse-bg { background-color: #000000; }

.ansi-bold { font-weight: bold; }
.ansi-underline { text-decoration: underline; }


div.nbinput.container div.input_area div[class*=highlight] > pre,
div.nboutput.container div.output_area div[class*=highlight] > pre,
div.nboutput.container div.output_area div[class*=highlight].math,
div.nboutput.container div.output_area.rendered_html,
div.nboutput.container div.output_area > div.output_javascript,
div.nboutput.container div.output_area:not(.rendered_html) > img{
    padding: 5px;
}

/* fix copybtn overflow problem in chromium (needed for 'sphinx_copybutton') */
div.nbinput.container div.input_area > div[class^='highlight'],
div.nboutput.container div.output_area > div[class^='highlight']{
    overflow-y: hidden;
}

/* hide copybtn icon on prompts (needed for 'sphinx_copybutton') */
.prompt a.copybtn {
    display: none;
}

/* Some additional styling taken form the Jupyter notebook CSS */
div.rendered_html table {
  border: none;
  border-collapse: collapse;
  border-spacing: 0;
  color: black;
  font-size: 12px;
  table-layout: fixed;
}
div.rendered_html thead {
  border-bottom: 1px solid black;
  vertical-align: bottom;
}
div.rendered_html tr,
div.rendered_html th,
div.rendered_html td {
  text-align: right;
  vertical-align: middle;
  padding: 0.5em 0.5em;
  line-height: normal;
  white-space: normal;
  max-width: none;
  border: none;
}
div.rendered_html th {
  font-weight: bold;
}
div.rendered_html tbody tr:nth-child(odd) {
  background: #f5f5f5;
}
div.rendered_html tbody tr:hover {
  background: rgba(66, 165, 245, 0.2);
}
</style>
<p>The input of this notebook is a dataset that has already been</p>
<div class="nbinput nblast docutils container">
<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[35]:
</pre></div>
</div>
<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre>
<span></span>import pandas as pd

import statsmodels.formula.api as smf
import statsmodels.api as sm

from src.conf import settings

TRAINING_DIR = settings.DATA_DIR / &quot;processed/training/&quot;

data = pd.read_parquet(TRAINING_DIR / &quot;0_labeled_data.parquet&quot;)
</pre></div>
</div>
</div>
<div class="nbinput docutils container">
<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[30]:
</pre></div>
</div>
<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre>
<span></span>data.head()
</pre></div>
</div>
</div>
<div class="nboutput nblast docutils container">
<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[30]:
</pre></div>
</div>
<div class="output_area rendered_html docutils container">
<div>
<style scoped>
    .dataframe tbody tr th:only-of-type {
        vertical-align: middle;
    }

    .dataframe tbody tr th {
        vertical-align: top;
    }

    .dataframe thead th {
        text-align: right;
    }
</style>
<table border="1" class="dataframe">
  <thead>
    <tr style="text-align: right;">
      <th></th>
      <th>timestamp</th>
      <th>is_weekday</th>
      <th>t</th>
      <th>dswrf</th>
      <th>SUNSD</th>
      <th>curtailment_event</th>
      <th>solar_curtailment</th>
      <th>load</th>
    </tr>
    <tr>
      <th>index</th>
      <th></th>
      <th></th>
      <th></th>
      <th></th>
      <th></th>
      <th></th>
      <th></th>
      <th></th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <th>0</th>
      <td>2017-02-01 00:00:00-08:00</td>
      <td>False</td>
      <td>282.630219</td>
      <td>204.382217</td>
      <td>2130985.0</td>
      <td>False</td>
      <td>8480.663464</td>
      <td>7.404797e+06</td>
    </tr>
    <tr>
      <th>1</th>
      <td>2017-02-02 00:00:00-08:00</td>
      <td>False</td>
      <td>282.440430</td>
      <td>155.364441</td>
      <td>1721099.0</td>
      <td>False</td>
      <td>288.956667</td>
      <td>7.367050e+06</td>
    </tr>
    <tr>
      <th>2</th>
      <td>2017-02-03 00:00:00-08:00</td>
      <td>False</td>
      <td>283.654236</td>
      <td>162.995560</td>
      <td>1762346.0</td>
      <td>False</td>
      <td>869.203799</td>
      <td>7.272859e+06</td>
    </tr>
    <tr>
      <th>3</th>
      <td>2017-02-04 00:00:00-08:00</td>
      <td>True</td>
      <td>283.166656</td>
      <td>197.639999</td>
      <td>1947685.0</td>
      <td>True</td>
      <td>69858.576657</td>
      <td>6.611103e+06</td>
    </tr>
    <tr>
      <th>4</th>
      <td>2017-02-05 00:00:00-08:00</td>
      <td>True</td>
      <td>283.199097</td>
      <td>174.813339</td>
      <td>2019408.0</td>
      <td>False</td>
      <td>25.348000</td>
      <td>6.661248e+06</td>
    </tr>
  </tbody>
</table>
</div></div>
</div>
<div class="nbinput nblast docutils container">
<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[ ]:
</pre></div>
</div>
<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre>
<span></span>
</pre></div>
</div>
</div>
<div class="nbinput nblast docutils container">
<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[39]:
</pre></div>
</div>
<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre>
<span></span>class ModelRun:

    def __init__(self, formula, data, threshold=.8):
        data = data.copy()
        self.formula = formula
        self.threshold = threshold
        self.test = data.sample(int(len(data)*.2//1))
        self.training = data[~data.index.isin(self.test.index)]

    def compute_performance(self, predictions):
        cutoff = self.threshold
        positive_predictions = predictions.query(&quot;probability &gt; @cutoff&quot;)[&quot;curtailment_event&quot;].value_counts()
        negative_predictions = predictions.query(&quot;probability &lt;= @cutoff&quot;)[&quot;curtailment_event&quot;].value_counts()

        true_positives = positive_predictions.loc[True]
        false_positives = positive_predictions.loc[False]

        true_negatives = negative_predictions.loc[False]
        false_negatives = negative_predictions[True]

        accuracy = (true_positives+true_negatives)/len(predictions)
        precision = true_positives / (true_positives + false_positives)

        self.performance = {
            &quot;true_positives&quot;: true_positives,
            &quot;false_positives&quot;: false_positives,
            &quot;true_negatives&quot;: true_negatives,
            &quot;false_negatives&quot;: false_negatives,
            &quot;accuracy&quot;: accuracy,
            &quot;precision&quot;: precision
        }

    def run(self):
        &quot;&quot;&quot;
        &quot;&quot;&quot;
        result = smf.glm(
            self.formula,
            self.training,
            family=sm.families.Binomial()
        ).fit()
        self.result = result

        # De-label our test data
        predictions = result.predict(
            self.test.drop(columns=[&quot;curtailment_event&quot;])
        )
        predictions.name = &quot;probability&quot;

        # We are predicting probability of False because patsy reverses categorical designations
        predictions = 1 - predictions

        # Validate our test data back to our predictions
        predictions = self.test.merge(predictions, left_index=True, right_index=True)

        self.predictions = predictions
        self.compute_performance(predictions)
</pre></div>
</div>
</div>
<div class="nbinput docutils container">
<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[65]:
</pre></div>
</div>
<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre>
<span></span>model_run = ModelRun(
    &quot;C(curtailment_event) ~ C(timestamp.dt.month) + C(is_weekday) + load + t + dswrf&quot;,
    data,
    0.8
)
model_run.run()
model_run.performance
</pre></div>
</div>
</div>
<div class="nboutput nblast docutils container">
<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[65]:
</pre></div>
</div>
<div class="output_area docutils container">
<div class="highlight"><pre>
{&#39;true_positives&#39;: 2,
 &#39;false_positives&#39;: 1,
 &#39;true_negatives&#39;: 51,
 &#39;false_negatives&#39;: 18,
 &#39;accuracy&#39;: 0.7361111111111112,
 &#39;precision&#39;: 0.6666666666666666}
</pre></div></div>
</div>
<div class="nbinput nblast docutils container">
<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[57]:
</pre></div>
</div>
<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre>
<span></span>
</pre></div>
</div>
</div>
<div class="nbinput nblast docutils container">
<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[ ]:
</pre></div>
</div>
<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre>
<span></span>
</pre></div>
</div>
</div>


      </div>
      <div class="bottomnav" role="navigation" aria-label="bottom navigation">
      
        <p>
        <a class="uplink" href="../index.html">Contents</a>
        </p>

      </div>

    <div class="footer" role="contentinfo">
        &#169; Copyright Thomas Tu, 2020.
      Created using <a href="http://sphinx-doc.org/">Sphinx</a> 2.4.4.
    </div>
  </body>
</html>