feat: Revamp utilities + sentiment analysis example (#62)

* chore: bump deps (#60) (#61)

* update with tfidf

* fix classifier output size

* remove dropout

* updated model

* update tester and analyzer

* add commands

* remove log

* completely revamp utilities

* delete split

---------

Co-authored-by: Dean Srebnik <[email protected]>

deno.jsonc

@@ -22,6 +22,8 @@
     "./utilities/image": "./packages/utilities/src/image/mod.ts",
     "./utilities/metrics": "./packages/utilities/src/metrics/mod.ts",
     "./utilities/encoding": "./packages/utilities/src/encoding/mod.ts",
+    "./utilities/mapper": "./packages/utilities/src/mapper/mod.ts",
+    "./utilities/transformer": "./packages/utilities/src/transformer/mod.ts",
     "./utilities/misc": "./packages/utilities/src/utils/mod.ts",
     // Tokenizers
     "./tokenizers": "./packages/tokenizers/mod.ts",
@@ -40,7 +42,9 @@
     "example:multiple-linear": "deno -A ./examples/multiple-linear/student.ts",
     "example:binary": "deno -A ./examples/classification/binary_iris.ts",
     "example:multiclass": "deno -A ./examples/classification/iris.ts",
-    "example:text-sentiment": "deno -A ./examples/sentiment-analysis/classifier.ts",
+    "example:sentiment-train": "deno -A ./examples/sentiment-analysis/classifier.ts",
+    "example:sentiment-test": "deno -A ./examples/sentiment-analysis/tester.ts",
+    "example:sentiment-try": "deno -A ./examples/sentiment-analysis/analyzer.ts",
     "example:text-spam": "deno -A ./examples/classification/spam.ts",
     "example:filters": "deno -A examples/filters/conv.ts ",
     "example:train": "deno -A examples/model/train.ts ",

examples/classification/spam.ts

@@ -94,7 +94,7 @@ net.train(
   // Train for 20 epochs
   20,
   2,
-  0.01
+  0.001
 );
 
 console.log(`training time: ${performance.now() - time}ms`);

examples/sentiment-analysis/analyzer.ts

@@ -1,70 +1,54 @@
 import { CPU, setupBackend, tensor } from "jsr:@denosaurs/[email protected]";
 import { Sequential } from "jsr:@denosaurs/[email protected]/core";
 
-import {
-  useSplit,
-  ClassificationReport,
-  MatrixLike,
-} from "jsr:@denosaurs/[email protected]/utilities";
+import type { MatrixLike } from "jsr:@denosaurs/[email protected]/utilities";
 
 import { CategoricalEncoder } from "jsr:@denosaurs/[email protected]/utilities/encoding";
 import {
-  CountVectorizer,
-  SplitTokenizer,
+    CountVectorizer,
+    SplitTokenizer,
+    TfIdfTransformer,
 } from "jsr:@denosaurs/[email protected]/utilities/text";
 
-import Mappings from "./mappings.json" with {type: "json"}
-import Vocab from "./vocab.json" with {type: "json"}
-
-
-console.time("Time Elapsed");
-
-console.log("\nImports loaded.");
-
+import Mappings from "./mappings.json" with { type: "json" };
+import Vocab from "./vocab.json" with { type: "json" };
+import Idf from "./tfidf.json" with { type: "json" };
 
 const vocab = new Map();
 
 for (const entry of Vocab) {
-    vocab.set(entry[0], entry[1])
+    vocab.set(entry[0], entry[1]);
 }
 
 const tokenizer = new SplitTokenizer({
-  skipWords: "english",
-  vocabulary: vocab,
-  standardize: { lowercase: true, stripNewlines: true },
+    skipWords: "english",
+    vocabulary: vocab,
+    standardize: { lowercase: true, stripNewlines: true },
 });
 
 const vectorizer = new CountVectorizer(tokenizer.vocabulary.size);
-
-console.log("\nX vectorized");
-console.timeLog("Time Elapsed");
+const transformer = new TfIdfTransformer({ idf: Float64Array.from(Idf) });
 
 const encoder = new CategoricalEncoder<string>();
 const mappings = new Map();
 
 for (const entry of Mappings) {
-    mappings.set(entry[0], entry[1])
+    mappings.set(entry[0], entry[1]);
 }
 
 encoder.mapping = mappings;
 
-console.log("\nCPU Backend Loading");
-console.timeLog("Time Elapsed");
-
 await setupBackend(CPU);
 
-console.log("\nCPU Backend Loaded");
-console.timeLog("Time Elapsed");
-
-const net = Sequential.loadFile("examples/sentiment-analysis/sentiment.st")
+const net = Sequential.loadFile("examples/sentiment-analysis/sentiment.st");
 
-const text = prompt("Text to analyze?") || "hello world"
+const text = prompt("Text to analyze?") || "hello world";
 
 const predYSoftmax = await net.predict(
-  tensor(vectorizer.transform(tokenizer.transform([text]), "f32"))
+    tensor(transformer.transform<"f32">(vectorizer.transform(tokenizer.transform([text]), "f32"))),
 );
 
 CategoricalEncoder.fromSoftmax<"f32">(predYSoftmax as MatrixLike<"f32">);
 const predY = encoder.untransform(predYSoftmax as MatrixLike<"f32">);
 
-console.log(`The sentiment predicted is ${predY[0]}`)
+console.log(`The sentiment predicted is ${predY[0]}`);

examples/sentiment-analysis/classifier.ts

@@ -2,13 +2,11 @@ import {
   AdamOptimizer,
   Cost,
   CPU,
-  Dropout1DLayer,
   Init,
   setupBackend,
   tensor,
 } from "jsr:@denosaurs/[email protected]";
 import { Sequential } from "jsr:@denosaurs/[email protected]/core";
-import { NadamOptimizer } from "jsr:@denosaurs/[email protected]/core/optimizers";
 import {
   DenseLayer,
   ReluLayer,
@@ -18,7 +16,7 @@ import {
 import {
   useSplit,
   ClassificationReport,
-  MatrixLike,
+  type MatrixLike,
 } from "jsr:@denosaurs/[email protected]/utilities";
 
 import { CategoricalEncoder } from "jsr:@denosaurs/[email protected]/utilities/encoding";
@@ -103,7 +101,7 @@ Deno.writeTextFileSync(
 );
 Deno.writeTextFileSync(
   "examples/sentiment-analysis/tfidf.json",
-  JSON.stringify(transformer.idf)
+  JSON.stringify(Array.from(transformer.idf as Float64Array))
 );
 
 console.log("\nCPU Backend Loading");
@@ -115,7 +113,7 @@ console.log("\nCPU Backend Loaded");
 console.timeLog("Time Elapsed");
 
 const net = new Sequential({
-  size: [4, vecX.nCols],
+  size: [4, tfidfX.nCols],
   layers: [
     DenseLayer({ size: [256], init: Init.Kaiming }),
     ReluLayer(),
@@ -127,7 +125,6 @@ const net = new Sequential({
     ReluLayer(),
     DenseLayer({ size: [16], init: Init.Kaiming }),
     ReluLayer(),
-    Dropout1DLayer({ probability: 0.5 }),
     DenseLayer({ size: [encoder.mapping.size], init: Init.Kaiming }),
     SoftmaxLayer(),
   ],

examples/sentiment-analysis/mappings.json

@@ -1 +1 @@
-[["empty",0],["sadness",1],["neutral",2],["worry",3],["surprise",4],["fun",5],["hate",6],["happiness",7],["enthusiasm",8],["love",9],["relief",10],["boredom",11],["anger",12]]
+[["empty",0],["sadness",1],["enthusiasm",2],["neutral",3],["worry",4],["surprise",5],["love",6],["fun",7],["hate",8],["happiness",9],["boredom",10],["relief",11],["anger",12]]

examples/sentiment-analysis/tester.ts

@@ -2,96 +2,79 @@ import { CPU, setupBackend, tensor } from "jsr:@denosaurs/[email protected]";
 import { Sequential } from "jsr:@denosaurs/[email protected]/core";
 
 import {
-  useSplit,
-  ClassificationReport,
-  MatrixLike,
+    ClassificationReport,
+    type MatrixLike,
+    useSplit,
 } from "jsr:@denosaurs/[email protected]/utilities";
 
 import { CategoricalEncoder } from "jsr:@denosaurs/[email protected]/utilities/encoding";
 import {
-  CountVectorizer,
-  SplitTokenizer,
+    CountVectorizer,
+    SplitTokenizer,
+    TfIdfTransformer,
 } from "jsr:@denosaurs/[email protected]/utilities/text";
 
-import Mappings from "./mappings.json" with {type: "json"}
-import Vocab from "./vocab.json" with {type: "json"}
+import Mappings from "./mappings.json" with { type: "json" };
+import Vocab from "./vocab.json" with { type: "json" };
+import Idf from "./tfidf.json" with { type: "json" };
 
 import { parse as parseCsv } from "jsr:@std/[email protected]/parse";
 
-
-console.time("Time Elapsed");
-
-console.log("\nImports loaded.");
-
 const file = Deno.readTextFileSync(
-    "examples/sentiment-analysis/text_emotion.csv"
-  );
-
-  console.log("\nData file loaded.");
-  console.timeLog("Time Elapsed");
-
-  const data = parseCsv(file, { skipFirstRow: true }) as {
+    "examples/sentiment-analysis/text_emotion.csv",
+);
+
+const data = parseCsv(file, { skipFirstRow: true }) as {
     sentiment: string;
     content: string;
-  }[];
-  const text = data.map((x) => x.content);
+}[];
+const text = data.map((x) => x.content);
 const labels = data.map((x) => x.sentiment);
 
-console.log("\nCSV Parsed");
-console.timeLog("Time Elapsed");
-
-const [[trainX, trainY], [testX, testY]] = useSplit(
-  { shuffle: true, ratio: [7, 3] },
-  text,
-  labels
+const [[_trainX, _trainY], [testX, testY]] = useSplit(
+    { shuffle: true, ratio: [7, 3] },
+    text,
+    labels,
 );
 
-console.log("Data Split");
-console.timeLog("Time Elapsed");
-
 const vocab = new Map();
 
 for (const entry of Vocab) {
-    vocab.set(entry[0], entry[1])
+    vocab.set(entry[0], entry[1]);
 }
 
 const tokenizer = new SplitTokenizer({
-  skipWords: "english",
-  vocabulary: vocab,
-  standardize: { lowercase: true, stripNewlines: true },
+    skipWords: "english",
+    vocabulary: vocab,
+    standardize: { lowercase: true, stripNewlines: true },
 });
 
 const vectorizer = new CountVectorizer(tokenizer.vocabulary.size);
 
-console.log("\nX vectorized");
-console.timeLog("Time Elapsed");
+const transformer = new TfIdfTransformer({ idf: Float64Array.from(Idf) });
 
 const encoder = new CategoricalEncoder<string>();
 const mappings = new Map();
 
 for (const entry of Mappings) {
-    mappings.set(entry[0], entry[1])
+    mappings.set(entry[0], entry[1]);
 }
 
 encoder.mapping = mappings;
 
-console.log("\nCPU Backend Loading");
-console.timeLog("Time Elapsed");
-
 await setupBackend(CPU);
 
-console.log("\nCPU Backend Loaded");
-console.timeLog("Time Elapsed");
-
-const net = Sequential.loadFile("examples/sentiment-analysis/sentiment.st")
+const net = Sequential.loadFile("examples/sentiment-analysis/sentiment.st");
 
 const predYSoftmax = await net.predict(
-  tensor(vectorizer.transform(tokenizer.transform(testX), "f32"))
+    tensor(
+        transformer.transform<"f32">(
+            vectorizer.transform(tokenizer.transform(testX), "f32"),
+        ),
+    ),
 );
 
 CategoricalEncoder.fromSoftmax<"f32">(predYSoftmax as MatrixLike<"f32">);
 const predY = encoder.untransform(predYSoftmax as MatrixLike<"f32">);
 
 console.log(new ClassificationReport(testY, predY));
-
-console.log(testY, predY)