diff --git a/image_preprocessing.ipynb b/image_preprocessing.ipynb
index c2737bfbc0a742b0ef6fc282b7c15f0eda81b6f6..08f64d7e153c9bbb678cb19f479c9802bbcce841 100644
--- a/image_preprocessing.ipynb
+++ b/image_preprocessing.ipynb
@@ -13,19 +13,10 @@
},
{
"cell_type": "code",
- "execution_count": 39,
+ "execution_count": 3,
"id": "d7e56e0e-7eec-429d-940b-c3337db4b4dc",
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "The autoreload extension is already loaded. To reload it, use:\n",
- " %reload_ext autoreload\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"%load_ext autoreload\n",
"%autoreload 2\n",
@@ -109,7 +100,7 @@
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": 4,
"id": "b8c4f292",
"metadata": {},
"outputs": [],
@@ -120,17 +111,17 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 5,
"id": "7e9702c3",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "'h:\\\\School\\\\Winter 2022\\\\DS Projects\\\\2018\\\\hvm-image-clf/data/Training_Images_'"
+ "'c:\\\\Users\\\\Bennett Nolan\\\\Desktop\\\\info442\\\\hvm-image-clf/data/Training_Images_'"
]
},
- "execution_count": 3,
+ "execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
@@ -152,7 +143,7 @@
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": 5,
"id": "0ba9148a",
"metadata": {},
"outputs": [
@@ -192,7 +183,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": 7,
"id": "e6d378d5",
"metadata": {},
"outputs": [
@@ -224,7 +215,7 @@
"name": "stderr",
"output_type": "stream",
"text": [
- "<ipython-input-5-4c0ddd092066>:5: FutureWarning: In a future version of pandas all arguments of DataFrame.drop except for the argument 'labels' will be keyword-only.\n",
+ "C:\\Users\\Bennett Nolan\\AppData\\Local\\Temp\\ipykernel_10700\\2944415004.py:5: FutureWarning: In a future version of pandas all arguments of DataFrame.drop except for the argument 'labels' will be keyword-only.\n",
" metadata.drop('dx',1).isna().groupby(\n"
]
}
@@ -290,7 +281,7 @@
},
{
"cell_type": "code",
- "execution_count": 29,
+ "execution_count": 9,
"id": "05398a91",
"metadata": {},
"outputs": [],
@@ -301,7 +292,7 @@
},
{
"cell_type": "code",
- "execution_count": 30,
+ "execution_count": 10,
"id": "e8642d8d",
"metadata": {},
"outputs": [],
@@ -311,7 +302,7 @@
},
{
"cell_type": "code",
- "execution_count": 31,
+ "execution_count": 11,
"id": "5312b5de",
"metadata": {},
"outputs": [],
@@ -321,7 +312,7 @@
},
{
"cell_type": "code",
- "execution_count": 32,
+ "execution_count": 12,
"id": "49338970",
"metadata": {},
"outputs": [],
@@ -331,7 +322,7 @@
},
{
"cell_type": "code",
- "execution_count": 33,
+ "execution_count": 13,
"id": "784d69cd",
"metadata": {},
"outputs": [],
@@ -341,23 +332,10 @@
},
{
"cell_type": "code",
- "execution_count": 35,
+ "execution_count": 14,
"id": "6cd167a7",
"metadata": {},
- "outputs": [
- {
- "ename": "KeyboardInterrupt",
- "evalue": "",
- "output_type": "error",
- "traceback": [
- "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
- "\u001b[1;32m<ipython-input-35-c19654a1d8a1>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mnv_images\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtransform\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdest_dir\u001b[0m \u001b[1;33m+\u001b[0m \u001b[1;34m'nv'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msize\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m200\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m150\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
- "\u001b[1;32mh:\\School\\Winter 2022\\DS Projects\\2018\\hvm-image-clf\\data_processing.py\u001b[0m in \u001b[0;36mtransform\u001b[1;34m(path, size)\u001b[0m\n\u001b[0;32m 50\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 51\u001b[0m \u001b[1;31m# concatenate different images\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 52\u001b[1;33m \u001b[0mfull_mat\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mconcatenate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfull_mat\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mimg_ts\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 53\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mUnboundLocalError\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 54\u001b[0m \u001b[1;31m# if not assigned yet, assign one\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
- "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
- ]
- }
- ],
+ "outputs": [],
"source": [
"#This takes a really long time to run even when cutting down the images size.\n",
"nv_images = transform(dest_dir + 'nv', size=(200, 150))"
@@ -365,7 +343,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 15,
"id": "4de5cec3",
"metadata": {},
"outputs": [],
@@ -375,7 +353,7 @@
},
{
"cell_type": "code",
- "execution_count": 36,
+ "execution_count": 16,
"id": "d92158fa",
"metadata": {},
"outputs": [
@@ -385,7 +363,7 @@
"(1113, 67500)"
]
},
- "execution_count": 36,
+ "execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
@@ -426,11 +404,200 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 7,
+ "id": "5d475aed",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>image_id</th>\n",
+ " <th>dx</th>\n",
+ " <th>age</th>\n",
+ " <th>sex</th>\n",
+ " <th>localization</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>ISIC_0027419</td>\n",
+ " <td>bkl</td>\n",
+ " <td>80.0</td>\n",
+ " <td>male</td>\n",
+ " <td>scalp</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>ISIC_0025030</td>\n",
+ " <td>bkl</td>\n",
+ " <td>80.0</td>\n",
+ " <td>male</td>\n",
+ " <td>scalp</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>ISIC_0026769</td>\n",
+ " <td>bkl</td>\n",
+ " <td>80.0</td>\n",
+ " <td>male</td>\n",
+ " <td>scalp</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>ISIC_0025661</td>\n",
+ " <td>bkl</td>\n",
+ " <td>80.0</td>\n",
+ " <td>male</td>\n",
+ " <td>scalp</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>ISIC_0031633</td>\n",
+ " <td>bkl</td>\n",
+ " <td>75.0</td>\n",
+ " <td>male</td>\n",
+ " <td>ear</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " image_id dx age sex localization\n",
+ "0 ISIC_0027419 bkl 80.0 male scalp\n",
+ "1 ISIC_0025030 bkl 80.0 male scalp\n",
+ "2 ISIC_0026769 bkl 80.0 male scalp\n",
+ "3 ISIC_0025661 bkl 80.0 male scalp\n",
+ "4 ISIC_0031633 bkl 75.0 male ear"
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "metadata.head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
"id": "6e579e93",
"metadata": {},
- "outputs": [],
- "source": []
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>age</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>0.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>85.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>median</th>\n",
+ " <td>50.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>51.863828</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>skew</th>\n",
+ " <td>-0.166802</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " age\n",
+ "min 0.000000\n",
+ "max 85.000000\n",
+ "median 50.000000\n",
+ "mean 51.863828\n",
+ "skew -0.166802"
+ ]
+ },
+ "execution_count": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "metadata.agg({\n",
+ " \"age\":[\"min\", \"max\", \"median\", \"mean\", \"skew\"] \n",
+ "})"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "ea361300",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "sex\n",
+ "female 4552\n",
+ "male 5406\n",
+ "unknown 57\n",
+ "Name: sex, dtype: int64"
+ ]
+ },
+ "execution_count": 9,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "metadata.groupby(\"sex\")[\"sex\"].count()"
+ ]
},
{
"cell_type": "markdown",
@@ -441,12 +608,92 @@
]
},
{
- "cell_type": "code",
- "execution_count": null,
+ "cell_type": "markdown",
"id": "bf51add8",
"metadata": {},
- "outputs": [],
- "source": []
+ "source": [
+ "Distributions for metadata including Age, Localization, Sex, and Diagnosis"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "id": "6681e88c",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Text(0.5, 1.0, 'Localization')"
+ ]
+ },
+ "execution_count": 14,
+ "metadata": {},
+ "output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ "<Figure size 1080x1080 with 2 Axes>"
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "fig =plt.figure(figsize=(15,15))\n",
+ "ax1 = fig.add_subplot(221)\n",
+ "metadata['sex'].value_counts().plot(kind='bar', ax=ax1)\n",
+ "ax1.set_title('Sex')\n",
+ "\n",
+ "ax2=fig.add_subplot(222)\n",
+ "metadata['localization'].value_counts().plot(kind='bar', ax=ax2)\n",
+ "ax2.set_title('Localization')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "id": "f6596829",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Text(0.5, 1.0, 'Diagnosis')"
+ ]
+ },
+ "execution_count": 15,
+ "metadata": {},
+ "output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "iVBORw0KGgoAAAANSUhEUgAAA3MAAAGyCAYAAABOYp1CAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/YYfK9AAAACXBIWXMAAAsTAAALEwEAmpwYAAA1bElEQVR4nO3debxlVX3n/c8XEKJGGUtEQIuOqEEfBywB23THiDKIETuJiLFDxZCQdDDRjk9rGU2IY5fpRMUnakIEhQQFnGIpRCxxio9hKAZBBkOJICBDaQEOOKG//mPvC4dLXarqDPfcdevzfr3u656z9j7rrH3OrTrnu/caUlVIkiRJktqy1bQbIEmSJEnafIY5SZIkSWqQYU6SJEmSGmSYkyRJkqQGGeYkSZIkqUGGOUmSJElqkGFOkiRJE5Hk75P8xbTbMZcklyd55rTbIQ0rrjMnza8knweeBDy8qn485eZIkjS0JNcCuwJ3AT8DrgBOAU6oqp9PsWnSFsErc9I8SrIU+C9AAc+fbmskSRqLX6+qhwCPAlYCrwZOnG6TpC2DYU6aX0cB5wLvB5bPFCbZOcknknw3yQVJ3pTkSwPbH5dkdZL1Sb6W5Ij5b7okSXOrqjuqahXwImB5kickeX+SNwEk2THJJ5OsS3Jbf3uPmccn2SvJF5N8L8lnkrwryT/325YmqSTLk3wzybeTvHbgsdsleUeSb/U/70iyXb9tl/65bu8/R/8tyVb9tmuTPLu/vV+SNf1n8S1J3jZ/r540HMOcNL+OAk7tfw5Osmtf/i7gB8DD6ULeYNB7MLAa+ADwMOBI4N1J9pnHdkuStEmq6nzgBrqeKIO2At5HdwXvkcAPgb8b2P4B4HxgZ+CvgN/ZQPW/AjwWOBD4yyS/3Je/FjgAeDLdUIb9gNf1217Zt2cJXZfQP6frITPb8cDxVfVQ4JeAMzbhcKWpMsxJ8yTJr9B9gJ1RVRcCXwd+O8nWwG8Cx1XVnVV1BXDywEOfB1xbVe+rqruq6mLgI8AL5/kQJEnaVN8CdhosqKrvVNVH+s+67wFvBn4VIMkjgacBf1lVP6mqLwGrNlDv66vqh1X1FeArdMEN4CXAG6rq1qpaB7yee8LgT4HdgEdV1U+r6t9qw5NG/BR4dJJdqur7VXXuKC+ANB8Mc9L8WQ58uqq+3d//QF+2BNgGuH5g38HbjwL277uH3J7kdroPrYdPvsmSJA1ld2D9YEGSByX5hyTXJfku8EVgh/6k5iOA9VV158BDBj8LZ9w8cPtO4Bf7248ArhvYdl1fBvB/gLXAp5Nck2TFHG0+GngMcFU/5OF5Gz1Kacq2mXYDpC1BkgcCRwBbJ5n5INoO2IF7ZgHbA/iPftueAw+/HvhCVT1nflorSdLwkjyNLsx9Cdh/YNMr6bpI7l9VNyd5MnAxEOAmYKckDxoIdIOfhRvzLbqTn5f39x/Zl9FfBXwl8MokTwA+m+SCqjpnsIKquhp4cT+e7jeADyfZuap+sBntkOaVV+ak+fECuimb96Hrz/9k4JeBf6MbR/dR4K/6s5aP68tmfBJ4TJLfSfKA/udpA+MEJEmauiQP7a9mnQb8c1VdNmuXh9CNk7s9yU7AcTMbquo6YA3dZ+G2SZ4O/PpmPP0HgdclWZJkF+AvgZnJU56X5NFJAtxB93l8n2UTkvz3JEv6JRVu74tdXkELmmFOmh/LgfdV1Ter6uaZH7qB3y8BXgZsT9d95J/oPpR+DHefUTyIbuKTb/X7vJXuyp4kSdP2iSTfo+tJ8lrgbcBLN7DfO4AHAt+mm9n5U7O2vwR4OvAd4E3A6fSfhZvgTXRh8FLgMuCivgxgb+AzwPeBfwfeXVWf20AdhwCXJ/k+3WQoR1bVDzfx+aWpcNFwaQFK8la6RcWXb3RnSZIWoSSnA1dV1XEb3VnaQnllTloA+nXknpjOfnSDsD827XZJkjRf+iEEv5RkqySHAIcD/zLlZkkLmhOgSAvDQ+i6Vj4CuAX4W+DjU22RJEnz6+F0Y8h3plsX7n/0y/FImoPdLCVJkiSpQXazlCRpSEkem+SSgZ/vJnlFkp2SrE5ydf97x37/JHlnkrVJLk2y70Bdy/v9r07ieFlJ0kZ5ZU6SpDHoFz6+kW5drWPpFkBe2S9QvGNVvTrJc4E/AZ7b73d8Ve3fT9O+BlgGFHAh8NSqum0axyJJasOCHjO3yy671NKlS6fdDEnSPLjwwgu/XVVLpt2OERwIfL2qrktyOPDMvvxk4PPAq+kmdDilujOp5ybZIclu/b6rq2o9QJLVdNOkf3CuJ/MzUpK2DPf3+bigw9zSpUtZs2bNtJshSZoHSa6bdhtGdCT3hK9dq+qm/vbNwK797d3p1uKacUNfNlf5nPyMlKQtw/19PjpmTpKkESXZFng+8KHZ2/qrcGMZ05DkmCRrkqxZt27dOKqUJDXMMCdJ0ugOBS6qqlv6+7f03Sfpf9/al98I7DnwuD36srnK76WqTqiqZVW1bMmSlnukSpLGwTAnSdLoXsy9x7etAmZmpFzOPetGrgKO6me1PAC4o++OeTZwUJId+5kvD+rLJEma04IeMydJ0kKX5MHAc4A/HCheCZyR5GjgOuCIvvwsupks1wJ3Ai8FqKr1Sd4IXNDv94aZyVAkSZqLYU6SpBFU1Q+AnWeVfYdudsvZ+xbdsgUbquck4KRJtFGStDjZzVKSJEmSGmSYkyRJkqQGGeYkSZIkqUGGOUmSJElqkGFOkiRJkhpkmJMkSZKkBhnmJEmSJKlBhjlJkiRJapBhTpIkSZIaZJiTJEmSpAZtM+0GDGPpijM3ab9rVx424ZZIktSWTf0MHQc/hyVpsrwyJ0mSJEkNMsxJkiRJUoMMc5IkSZLUIMOcJEmSJDXIMCdJkiRJDTLMSZIkSVKDDHOSJEmS1CDDnCRJkiQ1yDAnSZIkSQ0yzEmSJElSgwxzkiRJktQgw5wkSZIkNcgwJ0mSJEkNMsxJkiRJUoMMc5IkSZLUIMOcJEmSJDXIMCdJkiRJDTLMSZIkSVKDDHOSJEmS1CDDnCRJkiQ1yDAnSZIkSQ0yzEmSJElSgwxzkiRJktSgjYa5JCcluTXJVwfK/k+Sq5JcmuRjSXYY2PaaJGuTfC3JwQPlh/Rla5OsGPuRSJIkSdIWZFOuzL0fOGRW2WrgCVX1ROA/gNcAJNkHOBJ4fP+YdyfZOsnWwLuAQ4F9gBf3+0qSJEmShrDRMFdVXwTWzyr7dFXd1d89F9ijv304cFpV/biqvgGsBfbrf9ZW1TVV9RPgtH5fSZIkSdIQxjFm7veAf+1v7w5cP7Dthr5srvL7SHJMkjVJ1qxbt24MzZMkSZKkxWekMJfktcBdwKnjaQ5U1QlVtayqli1ZsmRc1UqSJEnSorLNsA9M8rvA84ADq6r64huBPQd226Mv437KJUmSJEmbaagrc0kOAV4FPL+q7hzYtAo4Msl2SfYC9gbOBy4A9k6yV5Jt6SZJWTVa0yVJkiRpy7XRK3NJPgg8E9glyQ3AcXSzV24HrE4CcG5V/VFVXZ7kDOAKuu6Xx1bVz/p6XgacDWwNnFRVl0/geIa2dMWZm7TftSsPm3BLJEmSJGnjNhrmqurFGyg+8X72fzPw5g2UnwWctVmtkyRJkiRt0Dhms5QkSZIkzTPDnCRJI0iyQ5IPJ7kqyZVJnp5kpySrk1zd/96x3zdJ3plkbZJLk+w7UM/yfv+rkyyf3hFJklphmJMkaTTHA5+qqscBTwKuBFYA51TV3sA5/X2AQ+kmB9sbOAZ4D0CSnejGpO8P7AccNxMAJUmai2FOkqQhJdke+K/0Y8mr6idVdTtwOHByv9vJwAv624cDp1TnXGCHJLsBBwOrq2p9Vd0GrAYOmbcDkSQ1yTAnSdLw9gLWAe9LcnGS9yZ5MLBrVd3U73MzsGt/e3fg+oHH39CXzVUuSdKcDHOSJA1vG2Bf4D1V9RTgB9zTpRKAqiqgxvFkSY5JsibJmnXr1o2jSklSwwxzkiQN7wbghqo6r7//Ybpwd0vffZL+96399huBPQcev0dfNlf5vVTVCVW1rKqWLVmyZKwHIklqj2FOkqQhVdXNwPVJHtsXHQhcAawCZmakXA58vL+9Cjiqn9XyAOCOvjvm2cBBSXbsJz45qC+TJGlOG100XJIk3a8/AU5Nsi1wDfBSupOlZyQ5GrgOOKLf9yzgucBa4M5+X6pqfZI3Ahf0+72hqtbP3yFIklpkmJMkaQRVdQmwbAObDtzAvgUcO0c9JwEnjbVxkqRFzW6WkiRJktQgw5wkSZIkNcgwJ0mSJEkNMsxJkiRJUoMMc5IkSZLUIMOcJEmSJDXIMCdJkiRJDTLMSZIkSVKDDHOSJEmS1CDDnCRJkiQ1yDAnSZIkSQ0yzEmSJElSgwxzkiRJktQgw5wkSZIkNcgwJ0mSJEkNMsxJkiRJUoMMc5IkSZLUIMOcJEmSJDXIMCdJkiRJDTLMSZIkSVKDDHOSJEmS1CDDnCRJkiQ1yDAnSZIkSQ0yzEmSJElSgwxzkiRJktQgw5wkSZIkNcgwJ0mSJEkNMsxJkiRJUoMMc5IkSZLUIMOcJEmSJDXIMCdJkiRJDTLMSZIkSVKDDHOSJEmS1CDDnCRJkiQ1yDAnSZIkSQ3aaJhLclKSW5N8daBspySrk1zd/96xL0+SdyZZm+TSJPsOPGZ5v//VSZZP5nAkSZIkacuwzSbs837g74BTBspWAOdU1cokK/r7rwYOBfbuf/YH3gPsn2Qn4DhgGVDAhUlWVdVt4zqQhWjpijM3ed9rVx42wZZIkiRJWmw2emWuqr4IrJ9VfDhwcn/7ZOAFA+WnVOdcYIckuwEHA6uran0f4FYDh4yh/ZIkSZK0RRp2zNyuVXVTf/tmYNf+9u7A9QP73dCXzVUuSZIkSRrCyBOgVFXRdZ0ciyTHJFmTZM26devGVa0kSZIkLSrDhrlb+u6T9L9v7ctvBPYc2G+Pvmyu8vuoqhOqallVLVuyZMmQzZMkSZKkxW3YMLcKmJmRcjnw8YHyo/pZLQ8A7ui7Y54NHJRkx37my4P6MkmSJEnSEDY6m2WSDwLPBHZJcgPdrJQrgTOSHA1cBxzR734W8FxgLXAn8FKAqlqf5I3ABf1+b6iq2ZOqSJIkSZI20UbDXFW9eI5NB25g3wKOnaOek4CTNqt1ug+XO5AkSZIEY5gARZKkLVmSa5NcluSSJGv6sp2SrE5ydf97x748Sd6ZZG2SS5PsO1DP8n7/q5Msn+v5JEmaYZiTJGl0v1ZVT66qZf39FcA5VbU3cE5/H+BQYO/+5xjgPdCFP7phDPsD+wHHzQRASZLmYpiTJGn8DgdO7m+fDLxgoPyU6pwL7NDPCn0wsLqq1lfVbcBq4JB5brMkqTGGOUmSRlPAp5NcmOSYvmzXfjZngJuBXfvbuwPXDzz2hr5srvJ7cS1WSdKgjU6AIkmS7tevVNWNSR4GrE5y1eDGqqokNY4nqqoTgBMAli1bNpY6JUnt8sqcJEkjqKob+9+3Ah+jG/N2S999kv73rf3uNwJ7Djx8j75srnJJkuZkmJMkaUhJHpzkITO3gYOArwKrgJkZKZcDH+9vrwKO6me1PAC4o++OeTZwUJId+4lPDurLJEmak90sJUka3q7Ax5JA95n6gar6VJILgDOSHA1cBxzR738W8FxgLXAn8FKAqlqf5I3ABf1+b6iq9fN3GJKkFhnmJEkaUlVdAzxpA+XfAQ7cQHkBx85R10nASeNuoyRp8bKbpSRJkiQ1yDAnSZIkSQ0yzEmSJElSgwxzkiRJktQgw5wkSZIkNcgwJ0mSJEkNMsxJkiRJUoMMc5IkSZLUIMOcJEmSJDXIMCdJkiRJDTLMSZIkSVKDDHOSJEmS1CDDnCRJkiQ1yDAnSZIkSQ0yzEmSJElSgwxzkiRJktQgw5wkSZIkNcgwJ0mSJEkNMsxJkiRJUoMMc5IkSZLUIMOcJEmSJDXIMCdJkiRJDTLMSZIkSVKDDHOSJEmS1CDDnCRJkiQ1yDAnSZIkSQ0yzEmSJElSgwxzkiRJktQgw5wkSZIkNcgwJ0mSJEkNMsxJkiRJUoMMc5IkSZLUIMOcJEmSJDXIMCdJkiRJDTLMSZIkSVKDDHOSJEmS1KCRwlyS/5nk8iRfTfLBJL+QZK8k5yVZm+T0JNv2+27X31/bb186liOQJEmSpC3Q0GEuye7AnwLLquoJwNbAkcBbgbdX1aOB24Cj+4ccDdzWl7+930+SJEmSNIRRu1luAzwwyTbAg4CbgGcBH+63nwy8oL99eH+ffvuBSTLi80uSJEnSFmmbYR9YVTcm+Rvgm8APgU8DFwK3V9Vd/W43ALv3t3cHru8fe1eSO4CdgW8P2waNx9IVZ27yvteuPGyCLZEkSZK0qUbpZrkj3dW2vYBHAA8GDhm1QUmOSbImyZp169aNWp0kSZIkLUqjdLN8NvCNqlpXVT8FPgo8A9ih73YJsAdwY3/7RmBPgH779sB3ZldaVSdU1bKqWrZkyZIRmidJkiRJi9coYe6bwAFJHtSPfTsQuAL4HPBb/T7LgY/3t1f19+m3f7aqaoTnlyRJkqQt1tBhrqrOo5vI5CLgsr6uE4BXA3+WZC3dmLgT+4ecCOzcl/8ZsGKEdkuStCAk2TrJxUk+2d/f7CV6krymL/9akoOndCiSpMYMPQEKQFUdBxw3q/gaYL8N7Psj4IWjPJ8kSQvQy4ErgYf292eW6Dktyd/TLc3zHgaW6Ekys5TPi5LsQ7e0z+PpxqB/Jsljqupn830gkqS2jLo0gSRJW6wkewCHAe/t74fNX6LncOC0qvpxVX0DWMsGTopKkjSbYU6SpOG9A3gV8PP+/s5s4hI9wMwSPXeXb+AxkiTNyTAnSdIQkjwPuLWqLpzH53T5HknS3QxzkiQN5xnA85NcC5xG173yeDZ/iZ67yzfwmHtx+R5J0iDDnCRJQ6iq11TVHlW1lG4Ck89W1UvY/CV6VgFH9rNd7gXsDZw/T4chSWrYSLNZSpKk+3g1cFqSNwEXc+8lev6pX6JnPV0ApKouT3IG3VqtdwHHOpOlJGlTGOYkSRpRVX0e+Hx/e7OX6KmqNwNvnlwLJUmLkWFOE7F0xZmbvO+1Kw+bYEskSZKkxckwp6Zsakg0IEqSJGmxcwIUSZIkSWqQYU6SJEmSGmSYkyRJkqQGGeYkSZIkqUGGOUmSJElqkLNZaovnDJmSJElqkVfmJEmSJKlBhjlJkiRJapBhTpIkSZIaZJiTJEmSpAYZ5iRJkiSpQYY5SZIkSWqQYU6SJEmSGmSYkyRJkqQGGeYkSZIkqUGGOUmSJElqkGFOkiRJkhpkmJMkSZKkBhnmJEmSJKlBhjlJkiRJapBhTpIkSZIaZJiTJEmSpAYZ5iRJkiSpQYY5SZIkSWqQYU6SJEmSGmSYkyRJkqQGGeYkSZIkqUGGOUmSJElqkGFOkiRJkhpkmJMkSZKkBhnmJEmSJKlBhjlJkiRJapBhTpIkSZIaZJiTJEmSpAYZ5iRJkiSpQdtMuwHSYrR0xZmbtN+1Kw+bcEskSZK0WHllTpIkSZIaNFKYS7JDkg8nuSrJlUmenmSnJKuTXN3/3rHfN0nemWRtkkuT7DueQ5AkSZKkLc+oV+aOBz5VVY8DngRcCawAzqmqvYFz+vsAhwJ79z/HAO8Z8bklSZIkaYs1dJhLsj3wX4ETAarqJ1V1O3A4cHK/28nAC/rbhwOnVOdcYIckuw37/JIkSZK0JRvlytxewDrgfUkuTvLeJA8Gdq2qm/p9bgZ27W/vDlw/8Pgb+rJ7SXJMkjVJ1qxbt26E5kmSJEnS4jVKmNsG2Bd4T1U9BfgB93SpBKCqCqjNqbSqTqiqZVW1bMmSJSM0T5IkSZIWr1HC3A3ADVV1Xn//w3Th7paZ7pP971v77TcCew48fo++TJKkJiX5hSTnJ/lKksuTvL4v3yvJef2kX6cn2bYv366/v7bfvnSgrtf05V9LcvCUDkmS1JChw1xV3Qxcn+SxfdGBwBXAKmB5X7Yc+Hh/exVwVD+r5QHAHQPdMSVJatGPgWdV1ZOAJwOH9J9xbwXeXlWPBm4Dju73Pxq4rS9/e78fSfYBjgQeDxwCvDvJ1vN5IJKk9ow6m+WfAKcmuZTuQ+wtwErgOUmuBp7d3wc4C7gGWAv8I/DHIz63JElT1U/q9f3+7gP6nwKeRddjBe47GdjMJGEfBg5Mkr78tKr6cVV9g+6zcr/JH4EkqWXbjPLgqroEWLaBTQduYN8Cjh3l+SRJWmj6K2gXAo8G3gV8Hbi9qu7qdxmc8OvuycCq6q4kdwA79+XnDlQ75yRhdMv78MhHPnLsxyJJasuoV+YkSdqiVdXPqurJdGPB9wMeN8HncpIwSdLdDHOSJI1Bv9bq54Cn062lOtP7ZXDCr7snA+u3bw98BycJkyQNwTAnSdKQkixJskN/+4HAc4Ar6ULdb/W7zZ4MbGaSsN8CPtsPQ1gFHNnPdrkXsDdw/rwchCSpWSONmZMkaQu3G3ByP25uK+CMqvpkkiuA05K8CbgYOLHf/0Tgn5KsBdbTzWBJVV2e5Ay6WaHvAo6tqp/N87FIkhpjmJMkaUhVdSnwlA2UX8MGZqOsqh8BL5yjrjcDbx53GyVJi5fdLCVJkiSpQYY5SZIkSWqQYU6SJEmSGmSYkyRJkqQGGeYkSZIkqUGGOUmSJElqkGFOkiRJkhpkmJMkSZKkBhnmJEmSJKlBhjlJkiRJapBhTpIkSZIaZJiTJEmSpAYZ5iRJkiSpQYY5SZIkSWqQYU6SJEmSGmSYkyRJkqQGGeYkSZIkqUGGOUmSJElqkGFOkiRJkhpkmJMkSZKkBhnmJEmSJKlBhjlJkiRJapBhTpIkSZIaZJiTJEmSpAYZ5iRJkiSpQYY5SZIkSWrQNtNugKRNs3TFmZu877UrD5tgSyRJkrQQeGVOkiRJkhpkmJMkSZKkBhnmJEmSJKlBhjlJkiRJapBhTpIkSZIaZJiTJEmSpAYZ5iRJkiSpQYY5SZIkSWqQYU6SJEmSGmSYkyRJkqQGGeYkSZIkqUGGOUmSJElqkGFOkiRJkho0cphLsnWSi5N8sr+/V5LzkqxNcnqSbfvy7fr7a/vtS0d9bkmSJEnaUo3jytzLgSsH7r8VeHtVPRq4DTi6Lz8auK0vf3u/nyRJkiRpCCOFuSR7AIcB7+3vB3gW8OF+l5OBF/S3D+/v028/sN9fkiRJkrSZthnx8e8AXgU8pL+/M3B7Vd3V378B2L2/vTtwPUBV3ZXkjn7/b4/YBklDWrrizE3e99qVh02wJZIkSdpcQ1+ZS/I84NaqunCM7SHJMUnWJFmzbt26cVYtSdJYJdkzyeeSXJHk8iQv78t3SrI6ydX97x378iR5Zz9+/NIk+w7Utbzf/+oky6d1TJKkdozSzfIZwPOTXAucRte98nhghyQzV/z2AG7sb98I7AnQb98e+M7sSqvqhKpaVlXLlixZMkLzJEmauLuAV1bVPsABwLFJ9gFWAOdU1d7AOf19gEOBvfufY4D3QBf+gOOA/YH9gONmAqAkSXMZOsxV1Wuqao+qWgocCXy2ql4CfA74rX635cDH+9ur+vv02z9bVTXs80uSNG1VdVNVXdTf/h7dhGC7c+9x4rPHj59SnXPpToDuBhwMrK6q9VV1G7AaOGT+jkSS1KJJrDP3auDPkqylGxN3Yl9+IrBzX/5n3HOWUpKk5vVL7jwFOA/Ytapu6jfdDOza3757/HhvZmz5XOWzn8OhCJKku406AQoAVfV54PP97WvouojM3udHwAvH8XySJC0kSX4R+Ajwiqr67uBkzVVVScbSE6WqTgBOAFi2bJm9WyRpCzeJK3OSJG0xkjyALsidWlUf7Ytv6btP0v++tS+/e/x4b2Zs+VzlkiTNyTAnSdKQ+vVSTwSurKq3DWwaHCc+e/z4Uf2slgcAd/TdMc8GDkqyYz/xyUF9mSRJcxpLN0tJkrZQzwB+B7gsySV92Z8DK4EzkhwNXAcc0W87C3gusBa4E3gpQFWtT/JG4IJ+vzdU1fp5OQJJUrMMc5IkDamqvgRkjs0HbmD/Ao6do66TgJPG1zpJ0mJnN0tJkiRJapBhTpIkSZIaZJiTJEmSpAYZ5iRJkiSpQYY5SZIkSWqQYU6SJEmSGmSYkyRJkqQGGeYkSZIkqUGGOUmSJElqkGFOkiRJkhpkmJMkSZKkBhnmJEmSJKlBhjlJkiRJapBhTpIkSZIaZJiTJEmSpAYZ5iRJkiSpQYY5SZIkSWqQYU6SJEmSGmSYkyRJkqQGGeYkSZIkqUGGOUmSJElq0DbTboCkxWXpijM3ed9rVx42wZZIkiQtbl6ZkyRJkqQGGeYkSZIkqUGGOUmSJElqkGFOkiRJkhpkmJMkSZKkBhnmJEmSJKlBhjlJkiRJapBhTpIkSZIaZJiTJEmSpAYZ5iRJkiSpQdtMuwGStDFLV5y5yfteu/KwCbZEkiRp4fDKnCRJkiQ1yDAnSZIkSQ0yzEmSJElSgwxzkiRJktQgw5wkSZIkNcgwJ0mSJEkNMsxJkiRJUoMMc5IkSZLUoKEXDU+yJ3AKsCtQwAlVdXySnYDTgaXAtcARVXVbkgDHA88F7gR+t6ouGq35kiRJsHTFmfP2XNeuPGzenkuS7s/QYQ64C3hlVV2U5CHAhUlWA78LnFNVK5OsAFYArwYOBfbuf/YH3tP/liRJ0gYYUiXdn6G7WVbVTTNX1qrqe8CVwO7A4cDJ/W4nAy/obx8OnFKdc4Edkuw27PNLkjRtSU5KcmuSrw6U7ZRkdZKr+9879uVJ8s4ka5NcmmTfgccs7/e/OsnyaRyLJKk9Yxkzl2Qp8BTgPGDXqrqp33QzXTdM6ILe9QMPu6EvkySpVe8HDplVtoKuh8rewDn9fbh3D5Vj6Hqo0A9POI6ut8p+wHEzAVCSpPszcphL8ovAR4BXVNV3B7dVVdGNp9uc+o5JsibJmnXr1o3aPEmSJqaqvgisn1W8uT1UDgZWV9X6qroNWM19A6IkSfcxUphL8gC6IHdqVX20L75lpvtk//vWvvxGYM+Bh+/Rl91LVZ1QVcuqatmSJUtGaZ4kSdOwuT1U7LkiSRrK0GGun53yRODKqnrbwKZVwEx//+XAxwfKj+rHDBwA3DHwYSdJ0qIzTA+V+2PvFUnSoFGuzD0D+B3gWUku6X+eC6wEnpPkauDZ/X2As4BrgLXAPwJ/PMJzS5K0UG1uD5VN6rkC9l6RJN3b0EsTVNWXgMyx+cAN7F/AscM+nyRJjZjpobKS+/ZQeVmS0+gmO7mjqm5KcjbwloFJTw4CXjPPbZYkNWiUdeYkSdqiJfkg8ExglyQ30M1KuRI4I8nRwHXAEf3uZwHPpeuhcifwUoCqWp/kjcAF/X5vqKrZk6pIknQfhjlJkoZUVS+eY9Nm9VCpqpOAk8bYNEnSFmAs68xJkiRJkuaXYU6SJEmSGmQ3S0lbrKUrztyk/a5dediEWyJJkrT5vDInSZIkSQ0yzEmSJElSgwxzkiRJktQgw5wkSZIkNcgwJ0mSJEkNMsxJkiRJUoMMc5IkSZLUIMOcJEmSJDXIMCdJkiRJDTLMSZIkSVKDDHOSJEmS1CDDnCRJkiQ1yDAnSZIkSQ0yzEmSJElSgwxzkiRJktQgw5wkSZIkNcgwJ0mSJEkN2mbaDZAkSdKWZ+mKM+ftua5dedi8PZc0n7wyJ0mSJEkNMsxJkiRJUoMMc5IkSZLUIMfMSdIYbeoYEMdvSJKkUXllTpIkSZIaZJiTJEmSpAbZzVKSFji7bkqSpA3xypwkSZIkNcgwJ0mSJEkNspulJEmSNCab2jV+HOxeL6/MSZIkSVKDDHOSJEmS1CDDnCRJkiQ1yDAnSZIkSQ0yzEmSJElSg5zNUpK2QC5ELklS+wxzkqSx2JzpuA2JkiSNzm6WkiRJktQgw5wkSZIkNchulpIkSZLu1+Z0pR8Hu+NvGsOcJEmSpC3WfAbVcYdUu1lKkiRJUoMMc5IkSZLUoHkPc0kOSfK1JGuTrJjv55ckaSHy81GStLnmNcwl2Rp4F3AosA/w4iT7zGcbJElaaPx8lCQNY76vzO0HrK2qa6rqJ8BpwOHz3AZJkhYaPx8lSZstVTV/T5b8FnBIVf1+f/93gP2r6mUD+xwDHNPffSzwtU2sfhfg22Ns7pZe56Tqtc4ts85J1Wudi6vOR1XVkjE/fxM25fOxLx/2M3JUk/p/YSFYrMfmcbVnsR6bxzW6OT8fF9zSBFV1AnDC5j4uyZqqWjbOtmzJdU6qXuvcMuucVL3WuWXWuSUb9jNyVIv5fVysx+ZxtWexHpvHNVnz3c3yRmDPgft79GWSJG3J/HyUJG22+Q5zFwB7J9krybbAkcCqeW6DJEkLjZ+PkqTNNq/dLKvqriQvA84GtgZOqqrLx1T9JLqdbMl1Tqpe69wy65xUvda5Zda56Ez483EcFvP7uFiPzeNqz2I9No9rguZ1AhRJkiRJ0njM+6LhkiRJkqTRGeYkSZIkqUGGOUmSJElqkGFOkiRJkuaQZK9pt2EuTU6AkmR74BBg977oRuDsqrp9odWb5HHA4bPqXFVVV45QZ4D9ZtV5fo3wZjb2mrbyPrXy3jfx9zSJ17Ovd1J/+7sO1llVt4xSX2uS7ARQVeun3RYNJ8mlwGnA6VX19Wm3Z1RJPgHM+f9aVT1/HpujzZDkWODUmf+Xk+wIvLiq3j3Vho0oyVuAv551XK+sqtdNtWEjSvJg4IdV9fP+/lbAL1TVndNt2fCSXFhVT01yTlUdOO32DGouzCU5CjgO+DT3LKi6B/Ac4PVVdcpCqTfJq4EX030Y3jBQ55HAaVW1cog6DwLeDVw9q52PBv64qj49RJ0tvaatvE+tvPdN/D1N4vWcYFufDPw9sP2sOm+ne00vGrKtkzg5MNYgm+SRwF8DB9Idb4CHAp8FVlTVtcO2VfMvyaOAF/U/PwdOB86oqm9OtWFDSvKr97e9qr4wX20ZtyTfowuq4d6BNUBV1UOn0rAxSXJJVT15VtnFVfWUKTVpLDZ0DEkuqqp9p9WmcUhyLvDsqvp+f/8XgU9X1X+ebsuGl+Ri4EPA/wDePnt7Vb1t3hvVazHMfQ3Yf/aXjf5sxnlV9ZiFUm+S/wAeX1U/nVW+LXB5Ve09RJ1XAofO/lLUX/49q6p+eYg6W3pNW3mfWnnvm/h7msTrOcG2XgL8YVWdN6v8AOAfqupJQ9Q5iZMDkwiy/w68A/hwVf2sL9saeCHwiqo6YHPr1MKQZG/gL4CXVNXW027PqJI8EHhkVX1t2m3RxiW5DHjiTI+R/v+VS6vq8dNt2Wj6q99Pq6of9/cfCKxZBMe1ofB9n7KWJHks8ALgFcB76E6UzKiqesMUmgXM86LhYzL7rNOMn3PvF3Yh1Ptz4BHAdbPKd+u3DWMb7vkyN+hG4AFD1tnSa9rK+9TKe9/K39MkXk+YTFsfPDvIAVTVuX3Xk2EczYbD7NuAy4Fhrky+FnjqXEEWGOaK/C5VdfpgQR/qTkvyxiHq05TNujr3M+BV023R6JL8OvA3wLbAXv3V9Dcshm6WSY6uqhNnla2sqhXTatOYfAo4Pck/9Pf/sC9r3anAOUne199/KXDyFNszLj9Isu9MT5QkTwV+OOU2jeow4Kd0vZl+MOW23EuLYe7NwEVJPg1c35c9ku5s8ihfFiZR7yvo/pFePavORwMvG7LOk4ALkpw2UOeedGfoT5zzUfevpde0lfdpEnVO4r1v5e/pFYz/9YTJtPVfk5xJF4YGX9OjGP7LxyTC7CSC7IVJ3k33ZWTw2JcDFw9Zp6YkyXl0J3XOAF5YVddMuUnj8ld044Q/D1BVl2QBT26wmX4zyY+q6lSAJO8CHjjlNo3Dq4Fj6Lq4AawG3ju95oxHVb01yVeAZ/dFb6yqs6fZpjF5BfChJN+i+zx5ON0JoZY9pP/9WOBpwMfpju3XgfOn1ShosJsl3H3m+GDuO87jtoVWbz/oc/bkEhfMdEEass5fZsNjZ64Yoc6WXtNW3qdW3vsm/p4m8XpOsK2HsuHX9Kwh6zsE+Du6sY33CbNVtdkhMcly4C/pulneJ8hW1fuHqHNbuquIg8d+A/AJ4MSZrkRqQz9O86nAoxg4+TvN7kTjkOTcqjpgcLxSkkur6onTbtuo+m56q+hO1B0C3F5VL59uq0bX92r40azu29u1PKHGjP7q995V9ZkkDwK2rqrvTbtdo0ryALrgA/C12T1LWpXki8BhM+9RkocAZ1bVf51am1oMc5K0pZnQyYGJnMTR4pDkU3QT2VxE18USgKr622m1aRySnAicA6wAfhP4U+ABVfVHU23YCNLPHtt7CN1Vgy/RnbBpflbZxTihBkCSP6C74rhTVf1SPzb172uBzZa4uZK8EPhUVX0vyeuAfYE3DTsB2ELSj7V/4sA4x+3oxm8+9v4fOTmLap25JCe0Um+ST06gzr+aQJ0tvaatvE+tvPeTqLOJ96ivdxJtPWbYx1bVz6vq3Kr6SP9z7qhXJavqtqo6rar+tv85bVJBLsnzJlGvJmqPqjqyqv564G+k6SDX+xPg8cCPgQ8AdwCtX726EFjT//4c3Wy6z+3L1kyxXePyCzNBDqC//aAptmdcjgWeAXwXoKquBh421RaNx1/0Qe5X6GY3PpFu0pDF4BTg/CR/1X9POg94/zQbtKjCHPAPG99lwdT7BxOo88IJ1NnSa9rK+9TKe9/K39MkXk+YTFtHmVBowxVO5uTAJE7iPG0CdWqyvpzk/5l2IyZgn/5nG+AX6LoFXzDVFo2oqvaqqv9Ed1zvAi7pf/4/uuDauh8kuXu6/iTLaH9CDYAfV9VPZu4k2Yb7WQuxITMnGg8D/rGqzqSbcKh5VfVmuolqbut/XlpV/3uabbKbpSRNUH9mcj/gqzXEun2bUP9uVXXTmOt8alUNFeYzocXdNf+SXEE3LvMbdFexZtYsa3psWd9N6v8FvsrABEJVNXuCoeYkOYPuKs+pfdFvA9tX1RHTa9XokjyNbmmWb/VFuwEvGvb/qYUiyV/TdWU+iu6K8R8DV1TVa6fZrlH1JxlvpBuDvS9d8D5/mKV5tHHNXZlL8sSB2w9I8rokq5K8pR84Omy92ydZmeSqJOuTfCfJlX3ZDkPWecis+k9McmmSDyTZdcg6t0nyh0k+1dd1aZJ/TfJH/WDTYeoc+7FPqt5JvP8Tep9aee8nUWcT79FAXeP+Gz1/4PYf0E1c8hDguCRjnx583EGur3PYIPdqui9coZvd6/z+9gcnceyauEOBvYGD6GZse17/u3XrquoTVfWNqrpu5mfajRqTJ1TV71fV5/qfPwCeMO1GjcFlwN/TnVRYR9dz4vKptmg8VtAdz2V0yy2cBbxuqi0ajyOAs4GD++VvdgL+11RbtIg1d2UuyUVVtW9/+2+BnYH30S3kt3NVHTVkvWcDnwVOrqqb+7KH002pfWBVHTRiW98L3Az8I/AbwK9W1QuGqPODdGdxTubeiwcvpxtAu9lTv07i2CdV7yTe/wm9T62895Oos4n3qK9rEn+jgzPkXQA8t6rWpZuN7dyq2uxua0kOmZmxMsn2wNvoui1+FfifVXXLEHVuD7yG7n15GF3XnlvpJk5YWbPWn9vEOieyuLs0TkkOBF5MNwnK3TOsVtVHp9aoMUnyz8DfVdW5/f39gWOH/W60UGTDVxx3qKoXTq9V2pgkD6PrygxAVX1zis1ZtFoMc4NflC4BnlZVP00S4CvDdv9I8rW5ZqK5v20bqXPwC+glNbDy/ez7m1Hnf1TVYzZ320bqHPuxT6reSbz/E3qfWnnvJ1FnE+9R/9hJ/I1+BXgmXc+Hs6tq2cC2u1+bzaxzEicHJhFkr6I7E3vdrPJH0c08N7XZvqQZfeB5HN2VnZlullVVvze9Vo0myWV0J2RmpoP/Zn//UcBVVbXPFJs3siRXzD6GDZW1IskZVXXEwPt2L4ugK/Pzgb+lWx/1Vrplb66qqsUwfnPBaXHR8O2T/De6L0rbzZwBrqpKMkoyvS7Jq+i+2NwC0Hff+l3uWYNpcz0syZ/RdTN6aJLUPel52C6u69NN+fqRqvp5386tgBfSDcQcxiSOfVL1bp/kN+he03G9/5N4n1p57ydRZyvvEUzob5Ru8pgAlX5MW7qptMcxAcqygfD69nTrxQ1jaVW9dbCgD3VvTTLsl9pXMJnF3aVxetoiPLGw2GeLvSjJAbOuOLY8S+fM7KmL9X17I3AA8JmqekqSXwP++5TbtGi1GOa+CDy/v31ukl2r6pb+jPK3R6j3RXR9l7/Qf5kr4Ba6xTeHHTj8j9yzYvzJwC7Aur6tlwxZ55HAW4F3J7mN7svh9nRTER85ZJ2TOPZJ1fsF7hmzMa73fxLv0yTf+3club0v24HR3vtJ1PkFug+osLDfI5jA32hVLZ1j08+B/zZMnUwmzI49yFbVp5I8hgks7i6N0ZeT7FNVV0y7IeMy+2r4YjHriuOXk9zriuM02zaKumes8z5V9a+D25L8Ed34wJb9tKq+k2SrJFtV1eeSvGPajVqsmutmuSFJThl3f/Ak/4XuC8llNaYZ6DLmWe2S7NzfPL6qhj7j0Z/huqqq7kg3QcUKutmHLgfeUlV3DFnvnwIfq6pRru5tqN79gZ9X1QVJ9gEOoWv/WSPUN/v4nwJcwZDHP+FjL+DrdN2Enk4389Wwx74t3diRb9EtDHwI3Zo3lwMnzB77tIl1bkcXBG+sqs8k+W3gPwNXDltnX+/j6ALCeTWw3lAGxpONUO8edOPZxlbvOCU5blbRu6sbh/dw4K+H+f8v3YLhK+hmnpxZ12gmyK4sFw7XIpXkSuCXWGSzdC5GfRftObUeYpN8GXhdVX22v/8q4Neq6tDptmw0ST5DNx57Jd24+Vvprog3vcj7QtVcmEuyagPFz6Ib+0FVPX8D2zel3vOrar/+9u/TLeT4L3SzeH2iqlaOoc6XAR8bsc6xH3+Sy4EnVdVd6daX+gHwEbqFHp9UVb+xuXX29d7R1/V1uoVZP1RVo1w9nflSeyjdVeXVdOH483TT355d3fofm1vn7OO/E/gwIxz/rGP/IN2xr9vcembVOYljP7Wv74F0C+c+mO5v9EC6/x82uwvfQJ0Poptc5ReBj/Z1UlW/O0Sdf0L37+dK4MnAy6vq4/22u8eTDVHvn9L9Wx9rvfMpyUur6n0LvU5poZgrILQeDNSeJLsAn6Sb6fEQupO0L66BtedalOS1dAtp30zXvXJ74NSq+s4027VYtRjmLqa7avBeuisUofuyfCRAVX1h2Hpr/DPQTaLOi+iuGI3t+JNcWVW/PFP/4BfYjDa5xMXAU4Fn03Vnez7dWKIPAh+tqu8NUedldF+6t6P7T2KPqvpukgfSXbEZZnKNsR9/Q8d+aVU9Md1CpTcCj6iqnyUjTVYyiTovA55eVd9PspQubP9TVR2fIScVmWS98ynJN6vqkQu9TknSfaWb8fEzdN8Rfm+gC32z+pPPRwDrgdPpTmhv9qzL2jQtjpl7Kt3A0dcC/6uqLknyw2FD3ICt+m5HW9GF3HUAVfWDJHctoDqXMf7j/+rAmfivJFlWVWv6sS9DdYnrVXWTanwa+HS6dcsOpevW9zfAkiHqvKsfe3Nnkq9X1Xf7J/phkp9v5LFzmcTxt3LsW/VdLR9MdyVte7r/fLejG6OwYOqc6QJZVdcmeSbw4f4M+yiTikyq3rFKculcm4Bh1y0ce52SpI1L8j3uOSFfwLbAfwJ+MwlV9dBptm9UVfV64PXp1p19Ed249Buq6tlTbtqi1FyY678gvz3Jh/rftzCe45jEDHRjr3NCx//7wPFJXkc3QcW/J7mebhKE3x+h3nsdYz9WahWwKsMv8P6TJA+qqjvpgn33RN2aWcMGmkkcfyvHfiLdIPKt6U4QfCjJNXSzUJ22gOq8JcmTq+oSgP5K2vOAk4DNvsI9D/WO267Awdx3htEAX15AdUqSNqKqZib0IslOwN4MrMe2iNxK15PoO9wzNltj1lw3y9mSHAY8o6r+fEL1PwjYtaq+sRDrHOfxJ3kosBddOLxh1EviSR5TVf8xartm1bldVf14A+W7ALtV1WUj1D2242/p2JM8AqCqvpVkB7quod+sqvNHaOtY60yyB92VyZs3sO0ZVfX/L6R6xy3JicD7qupLG9j2gar67YVQpyRp06WbT+HldJNwXUJ30vPLVXXgNNs1qiR/TNfNcgnwIeCMWkSzxy40zYc5SZIkqTX9uO2n0c2j8OR0syu/pYaceG6hSPK/gdNner1osprrZilJkiQtAj+qqh8lmel9c1WS5he0r6rXTLsNWxLDnCRJkjT/buiHIvwLsDrJbYBLZGiz2M1SkiRJmqIkv0o3cd6nWl9nTvPLMCdJkiRJDdpq2g2QJEmSJG0+w5wkSZIkNcgwJ0mSJEkNMsxJkiRJUoMMc5IkSZLUoP8LGnuLzRQRO0IAAAAASUVORK5CYII=",
+ "text/plain": [
+ "<Figure size 1080x1080 with 2 Axes>"
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "fig =plt.figure(figsize=(15,15))\n",
+ "ax1 = fig.add_subplot(221)\n",
+ "metadata['age'].value_counts().plot(kind='bar', ax=ax1)\n",
+ "ax1.set_title('Age')\n",
+ "\n",
+ "ax2=fig.add_subplot(222)\n",
+ "metadata['dx'].value_counts().plot(kind='bar', ax=ax2)\n",
+ "ax2.set_title('Diagnosis')"
+ ]
},
{
"cell_type": "markdown",
@@ -456,13 +703,122 @@
"Correlation"
]
},
+ {
+ "cell_type": "markdown",
+ "id": "fbc246dd",
+ "metadata": {},
+ "source": [
+ "Cross Tabulation of Age and Dx (Skin Lesion)\n",
+ "nv = Melanocytic nevi\n",
+ "mel = Melanoma\n",
+ "bkl = Benign keratosis-like lesions\n",
+ "bcc = Basal cell carcinoma\n",
+ "akiec = Actinic keratosis\n",
+ "vas = Vascular lesions\n",
+ "df = Dermatofibroma"
+ ]
+ },
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 34,
"id": "a0602660",
"metadata": {},
- "outputs": [],
- "source": []
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "dx akiec bcc bkl df mel nv vasc\n",
+ "age \n",
+ "0.0 0 0 5 0 0 30 4\n",
+ "5.0 0 0 1 0 1 81 3\n",
+ "10.0 0 0 0 0 0 39 2\n",
+ "15.0 0 0 0 0 0 73 4\n",
+ "20.0 0 1 0 0 6 158 4\n",
+ "25.0 0 3 0 2 16 221 5\n",
+ "30.0 1 4 6 4 34 410 5\n",
+ "35.0 0 5 24 12 36 668 8\n",
+ "40.0 9 23 46 9 49 846 3\n",
+ "45.0 10 26 59 14 74 1100 16\n",
+ "50.0 19 27 87 18 96 928 12\n",
+ "55.0 27 25 95 13 142 686 21\n",
+ "60.0 58 35 131 9 106 454 10\n",
+ "65.0 38 79 108 18 133 351 4\n",
+ "70.0 56 85 183 4 166 248 14\n",
+ "75.0 47 76 153 9 91 231 11\n",
+ "80.0 37 73 98 3 85 97 11\n",
+ "85.0 25 52 93 0 76 39 5\n"
+ ]
+ }
+ ],
+ "source": [
+ "ct = pd.crosstab(index=metadata['age'], columns=metadata['dx'])\n",
+ "print(ct)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 23,
+ "id": "0a82f299",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "dx akiec bcc bkl df mel nv vasc\n",
+ "sex \n",
+ "female 106 197 463 52 424 3237 73\n",
+ "male 221 317 626 63 689 3421 69\n",
+ "unknown 0 0 10 0 0 47 0\n"
+ ]
+ }
+ ],
+ "source": [
+ "ct2 = pd.crosstab(index=metadata['sex'], columns=metadata['dx'])\n",
+ "print(ct2)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 33,
+ "id": "ad813357",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "PValue = 2.4464388098587195e-17\n"
+ ]
+ }
+ ],
+ "source": [
+ "from scipy.stats import chi2_contingency\n",
+ "#Sex & Localization\n",
+ "chi2= chi2_contingency(ct2)\n",
+ "print(\"PValue = \" , chi2[1])\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "id": "20474e6b",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "PValue = 0.0\n"
+ ]
+ }
+ ],
+ "source": [
+ "#Age & DX\n",
+ "chi2_2= chi2_contingency(ct)\n",
+ "print(\"PValue = \" , chi2_2[1])"
+ ]
},
{
"cell_type": "markdown",
@@ -633,7 +989,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.9.0"
+ "version": "3.10.2"
}
},
"nbformat": 4,