{ "cells": [ { "cell_type": "markdown", "metadata": { "_cell_guid": "085d9848-e618-b058-fa96-16302b73dc4f" }, "source": [] }, { "cell_type": "code", "execution_count": 1, "metadata": { "_cell_guid": "76c6c1c2-ee11-8dcc-76d5-dd0dd98c4d9c" }, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "_cell_guid": "f006da23-48bd-5539-b720-b4e1ea3719f0" }, "outputs": [], "source": [ "from glob import glob\n", "\n", "def make_base_df():\n", " base_path = '../input/train'\n", " image_paths = []\n", " for type_base_path in sorted(glob(base_path +'/*')):\n", " image_paths = image_paths + glob(type_base_path + '/*')\n", " df = pd.DataFrame({'path':image_paths})\n", " df['type'] = df.path.map(lambda x: x.split('/')[-2])\n", " df['filetype'] = df.path.map(lambda x: x.split('.')[-1])\n", " df['num_id'] = df.path.map(lambda x:x.split('/')[-1].split('.')[0])\n", " return df" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "_cell_guid": "12b2c343-7eb6-580c-d246-9ce2996e7f8c" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[[ 15 13 12]\n", " [ 12 11 7]\n", " [ 12 13 9]\n", " ..., \n", " [ 41 29 27]\n", " [ 40 29 25]\n", " [ 40 30 23]]\n", "\n", " [[ 14 12 11]\n", " [ 13 12 8]\n", " [ 14 15 11]\n", " ..., \n", " [ 42 30 28]\n", " [ 43 32 28]\n", " [ 44 34 27]]\n", "\n", " [[ 11 12 10]\n", " [ 12 13 9]\n", " [ 14 15 11]\n", " ..., \n", " [ 42 30 28]\n", " [ 43 32 28]\n", " [ 44 34 27]]\n", "\n", " ..., \n", " [[162 115 101]\n", " [163 116 102]\n", " [163 115 103]\n", " ..., \n", " [ 45 26 21]\n", " [ 42 24 17]\n", " [ 43 25 18]]\n", "\n", " [[162 114 102]\n", " [162 114 102]\n", " [159 114 101]\n", " ..., \n", " [ 43 24 19]\n", " [ 42 24 17]\n", " [ 41 24 15]]\n", "\n", " [[164 116 104]\n", " [162 114 102]\n", " [159 114 101]\n", " ..., \n", " [ 44 25 20]\n", " [ 42 24 17]\n", " [ 41 24 15]]]\n" ] } ], "source": [ "import cv2\n", "\n", "df = make_base_df()\n", "path = df.path[1]\n", "img = cv2.imread(path)\n", "print(img)" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "_cell_guid": "d3e62342-ddb2-1e29-f821-b2d61aa75173" }, "outputs": [], "source": [ "import cv2\n", "\n", "def get_grayscale_img(path, rescale_dim):\n", " img = cv2.imread(path)\n", " rescaled = cv2.resize(img, (rescale_dim, rescale_dim), cv2.INTER_LINEAR)\n", " gray = cv2.cvtColor(rescaled, cv2.COLOR_RGB2GRAY).astype('float')\n", " return gray\n", "\n", "def save_img(img, num_id, desc):\n", " path = desc+num_id+\".jpg\"\n", " cv2.imwrite(path,img)\n", " return path\n", " \n", "def save_grayscale(row, desc):\n", " path = row.path\n", " num_id = row.num_id\n", " gray = get_grayscale_img(path, 100)\n", " return save_img(gray, num_id, desc)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "_cell_guid": "1c769433-d47b-0157-c1d7-f61999d07e39" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/opt/conda/lib/python3.6/site-packages/pandas/core/indexing.py:297: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n", " self.obj[key] = _infer_fill_value(value)\n", "/opt/conda/lib/python3.6/site-packages/pandas/core/indexing.py:477: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n", " self.obj[item] = s\n", "/opt/conda/lib/python3.6/site-packages/pandas/core/indexing.py:141: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame\n", "\n", "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n", " self._setitem_with_indexer(indexer, value)\n", "/opt/conda/lib/python3.6/site-packages/ipykernel/__main__.py:5: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame\n", "\n", "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n" ] }, { "data": { "text/html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
pathtypefiletypenum_idgray_path
0../input/train/Type_1/0.jpgType_1jpg0gray_0.jpg
1../input/train/Type_1/10.jpgType_1jpg10gray_10.jpg
2../input/train/Type_1/1013.jpgType_1jpg1013gray_1013.jpg
3../input/train/Type_1/1014.jpgType_1jpg1014gray_1014.jpg
4../input/train/Type_1/1019.jpgType_1jpg1019gray_1019.jpg
\n", "
" ], "text/plain": [ " path type filetype num_id gray_path\n", "0 ../input/train/Type_1/0.jpg Type_1 jpg 0 gray_0.jpg\n", "1 ../input/train/Type_1/10.jpg Type_1 jpg 10 gray_10.jpg\n", "2 ../input/train/Type_1/1013.jpg Type_1 jpg 1013 gray_1013.jpg\n", "3 ../input/train/Type_1/1014.jpg Type_1 jpg 1014 gray_1014.jpg\n", "4 ../input/train/Type_1/1019.jpg Type_1 jpg 1019 gray_1019.jpg" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = make_base_df()\n", "small_df = df[:100]\n", "desc = 'gray_'\n", "for index, row in small_df.iterrows():\n", " small_df.loc[index,'gray_path'] = save_grayscale(row, desc)\n", " \n", "small_df.head()" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "_cell_guid": "91ab5ce0-8693-2abc-986e-dc262e00afaa" }, "outputs": [ { "ename": "SyntaxError", "evalue": "invalid syntax (, line 5)", "output_type": "error", "traceback": [ "\u001b[0;36m File \u001b[0;32m\"\"\u001b[0;36m, line \u001b[0;32m5\u001b[0m\n\u001b[0;31m for\u001b[0m\n\u001b[0m ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m invalid syntax\n" ] } ], "source": [ "import matplotlib.pyplot as plt\n", "\n", "df = make_base_df()\n", "small_df = df[:100]\n", "for \n", "path = df.path[1]\n", "grey = get_grayscale_img(path, 100)\n", "cv2.imwrite(\"grey.jpg\", grey)\n", "plt.imshow(plt.imread(\"grey.jpg\"))" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "_cell_guid": "2f77dd83-b374-06bf-49d3-780f3e1cea62" }, "outputs": [ { "ename": "NameError", "evalue": "name 'plt' is not defined", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimshow\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", "\u001b[0;31mNameError\u001b[0m: name 'plt' is not defined" ] } ], "source": [ "plt.imshow(plt.imread(path))" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "_cell_guid": "189e709e-8714-ea7e-08b1-8b5f34484995" }, "outputs": [ { "ename": "NameError", "evalue": "name 'plt' is not defined", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimshow\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"grey.jpg\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", "\u001b[0;31mNameError\u001b[0m: name 'plt' is not defined" ] } ], "source": [ "plt.imshow(plt.imread(\"grey.jpg\"))" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "_cell_guid": "d871da50-0ab0-389b-e229-4718f363a55f" }, "outputs": [], "source": [ "from sklearn.ensemble import RandomForestClassifier as RFC\n", "\n", "forest = RFC(n_jobs=2,n_estimators=50)\n", "\n" ] } ], "metadata": { "_change_revision": 518, "_is_fork": false, "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": "3.6.0" } }, "nbformat": 4, "nbformat_minor": 0 }