asda

Untitled.ipynb

@@ -0,0 +1,89 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "8841693e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import joblib"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "44508d4e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "explainer = joblib.load('explainer.joblib')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "1b4565fa",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "FileNotFoundError",
+     "evalue": "[Errno 2] No such file or directory: 'ppl_labels.joblib'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-5-67089289c8c9>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mppl_labels\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mjoblib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mload\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'ppl_labels.joblib'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[0;32m~/opt/anaconda3/lib/python3.8/site-packages/joblib/numpy_pickle.py\u001b[0m in \u001b[0;36mload\u001b[0;34m(filename, mmap_mode)\u001b[0m\n\u001b[1;32m    575\u001b[0m             \u001b[0mobj\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_unpickle\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfobj\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    576\u001b[0m     \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 577\u001b[0;31m         \u001b[0;32mwith\u001b[0m \u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'rb'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    578\u001b[0m             \u001b[0;32mwith\u001b[0m \u001b[0m_read_fileobject\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmmap_mode\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mfobj\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    579\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfobj\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'ppl_labels.joblib'"
+     ]
+    }
+   ],
+   "source": [
+    "ppl_labels = joblib.load('ppl_labels.joblib')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "62b796d3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "shap.explainers._tree.Tree"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "type(explainer)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

app.py

@@ -9,6 +9,7 @@ import streamlit as st
 import streamlit.components.v1 as components
 import pickle
 import xgboost
+import joblib
 
 
 
@@ -56,10 +57,24 @@ st.title("Boba Leaderboard")
 
 #load joblib
 df_M_character = pickle.load(open('df_M_character.pickle', 'rb'))
-explainer = pickle.load(open('explainer.pickle', 'rb'))
-shap_values = pickle.load(open('shap_values.pickle', 'rb'))
+# explainer = pickle.load(open('explainer.pickle', 'rb'))
+# shap_values = pickle.load(open('shap_values.pickle', 'rb'))
 df_M_character_scale = scale_and_standardize(df_M_character)
 author_idx_lookup = dict([(name, idx) for idx, name in enumerate(df_M_character.index)])
+ppl_labels = joblib.load('ppl_labels.joblib') 
+# train XGBoost model
+X, y = pd.DataFrame(
+    df_M_character_scale, 
+    columns=df_M_character.columns
+), ppl_labels
+
+bst = xgboost.train({"learning_rate": 0.01}, xgboost.DMatrix(X, label=y), 100)
+
+# explain the model's predictions using SHAP values
+explainer = shap.TreeExplainer(bst)
+shap_values = explainer.shap_values(X)
+# shap.summary_plot(shap_values, X)
+
 
 X = pd.DataFrame(
     df_M_character_scale, 
@@ -71,8 +86,6 @@ df_leaderboard.rename(columns = {'Unnamed: 0':'Rank', 'author':'member'}, inplac
 selection = aggrid_interactive_table(df=df_leaderboard)
 
 
-
-
 if selection:
     try: 
         auth = selection["selected_rows"][0]['member']