From e5e37ebea95a606e39b887fb4e5b776d91ae0eda Mon Sep 17 00:00:00 2001
From: ltcptgeneral <learthurgo@gmail.com>
Date: Mon, 4 Dec 2023 10:22:45 -0800
Subject: [PATCH] extract lasso features

---
 linear_bow.ipynb  | 66 +++++++++++++++++++++++++++++++++++------------
 preliminary.ipynb |  4 +--
 2 files changed, 52 insertions(+), 18 deletions(-)

diff --git a/linear_bow.ipynb b/linear_bow.ipynb
index b917b2a..cfa1c17 100644
--- a/linear_bow.ipynb
+++ b/linear_bow.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -15,7 +15,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -64,7 +64,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -73,7 +73,7 @@
        "97248"
       ]
      },
-     "execution_count": 33,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -97,7 +97,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -111,7 +111,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -129,7 +129,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -169,7 +169,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -190,18 +190,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "0.01 0.21632227671715168 0.6847807364903296\n",
-      "0.1 0.2156867944836758 0.6829965387241808\n",
-      "1 0.21316700811628655 0.6747810400313006\n",
-      "10 0.2161776145305841 0.6681779252365153\n",
-      "100 0.20723445731519957 0.5973124724751776\n"
+      "0.01 0.21632227671897006 0.6847807364939246\n",
+      "0.1 0.21568679448554554 0.6829965387278908\n",
+      "1 0.21316700811782532 0.6747810400344023\n",
+      "10 0.21617761453133164 0.6681779252378663\n",
+      "100 0.20723445731522736 0.5973124724752429\n"
      ]
     }
    ],
@@ -226,7 +226,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -236,7 +236,7 @@
       "0.01 0.17702951629340366 0.538690243296189\n",
       "0.1 0.177432503566242 0.5387345171140366\n",
       "1 0.17743138596037397 0.538778156304091\n",
-      "10 0.17786269625555318 0.5396020974919651\n",
+      "10 0.17786269625555318 0.539602097491965\n",
       "100 0.17818192454918605 0.557911382661004\n"
      ]
     }
@@ -257,6 +257,40 @@
     "\n",
     "    print(C, mean_squared_error(Y_funny_test, pred_funny_test), mean_squared_error(Y_helpful_test, pred_helpful_test))"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "-0.008666338118757945: you\n",
+      "-0.0033743830081447994: shit\n",
+      "0.002818066343305709: i\n",
+      "-0.0009495127061038011: 3\n",
+      "-0.0007321653144316716: it\n",
+      "0.0006758513650775456: bad\n",
+      "-0.0005113655228402811: nyan\n",
+      "-0.00045892382707229636: of\n",
+      "0.0003103226245059089: *review length*\n",
+      "-0.00026518360080170943: ͡°\n"
+     ]
+    }
+   ],
+   "source": [
+    "model = linear_model.Lasso(alpha=0.01, fit_intercept=True)\n",
+    "model.fit(X_train, Y_helpful_train)\n",
+    "idxs = np.argsort(np.abs(model.coef_))[::-1][:10]\n",
+    "\n",
+    "for idx in idxs:\n",
+    "    if (idx < len(words)):\n",
+    "        print(f\"{model.coef_[idx]}: {words[idx]}\")\n",
+    "    else:\n",
+    "        print(f\"{model.coef_[idx]}: *review length*\")"
+   ]
   }
  ],
  "metadata": {
diff --git a/preliminary.ipynb b/preliminary.ipynb
index 55037ff..eebf99f 100644
--- a/preliminary.ipynb
+++ b/preliminary.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "9808cacf",
    "metadata": {},
    "outputs": [],
@@ -16,7 +16,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "494d6c25",
    "metadata": {},
    "outputs": [],