Created
August 23, 2017 08:04
-
-
Save infinite-Joy/a7cc8a9975f12b33a896eb6c3412448d to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": 1, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/html": [ | |
"<div>\n", | |
"<style>\n", | |
" .dataframe thead tr:only-child th {\n", | |
" text-align: right;\n", | |
" }\n", | |
"\n", | |
" .dataframe thead th {\n", | |
" text-align: left;\n", | |
" }\n", | |
"\n", | |
" .dataframe tbody tr th {\n", | |
" vertical-align: top;\n", | |
" }\n", | |
"</style>\n", | |
"<table border=\"1\" class=\"dataframe\">\n", | |
" <thead>\n", | |
" <tr style=\"text-align: right;\">\n", | |
" <th></th>\n", | |
" <th>Date</th>\n", | |
" <th>Open</th>\n", | |
" <th>High</th>\n", | |
" <th>Low</th>\n", | |
" <th>Last</th>\n", | |
" <th>Close</th>\n", | |
" <th>Total Trade Quantity</th>\n", | |
" <th>Turnover (Lacs)</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>2017-08-02</td>\n", | |
" <td>209.10</td>\n", | |
" <td>209.95</td>\n", | |
" <td>204.1</td>\n", | |
" <td>205.80</td>\n", | |
" <td>206.70</td>\n", | |
" <td>2935.0</td>\n", | |
" <td>6.09</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>1</th>\n", | |
" <td>2017-08-01</td>\n", | |
" <td>212.00</td>\n", | |
" <td>214.95</td>\n", | |
" <td>208.3</td>\n", | |
" <td>208.30</td>\n", | |
" <td>209.15</td>\n", | |
" <td>5094.0</td>\n", | |
" <td>10.78</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>2</th>\n", | |
" <td>2017-07-31</td>\n", | |
" <td>212.00</td>\n", | |
" <td>215.00</td>\n", | |
" <td>210.2</td>\n", | |
" <td>210.35</td>\n", | |
" <td>212.00</td>\n", | |
" <td>6803.0</td>\n", | |
" <td>14.47</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>3</th>\n", | |
" <td>2017-07-28</td>\n", | |
" <td>208.00</td>\n", | |
" <td>213.95</td>\n", | |
" <td>208.0</td>\n", | |
" <td>211.95</td>\n", | |
" <td>211.25</td>\n", | |
" <td>2023.0</td>\n", | |
" <td>4.28</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>4</th>\n", | |
" <td>2017-07-27</td>\n", | |
" <td>213.05</td>\n", | |
" <td>215.30</td>\n", | |
" <td>209.0</td>\n", | |
" <td>210.95</td>\n", | |
" <td>210.50</td>\n", | |
" <td>6714.0</td>\n", | |
" <td>14.23</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" Date Open High Low Last Close Total Trade Quantity \\\n", | |
"0 2017-08-02 209.10 209.95 204.1 205.80 206.70 2935.0 \n", | |
"1 2017-08-01 212.00 214.95 208.3 208.30 209.15 5094.0 \n", | |
"2 2017-07-31 212.00 215.00 210.2 210.35 212.00 6803.0 \n", | |
"3 2017-07-28 208.00 213.95 208.0 211.95 211.25 2023.0 \n", | |
"4 2017-07-27 213.05 215.30 209.0 210.95 210.50 6714.0 \n", | |
"\n", | |
" Turnover (Lacs) \n", | |
"0 6.09 \n", | |
"1 10.78 \n", | |
"2 14.47 \n", | |
"3 4.28 \n", | |
"4 14.23 " | |
] | |
}, | |
"execution_count": 1, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"import pandas as pd\n", | |
"from sklearn.ensemble import RandomForestClassifier\n", | |
"import numpy as np\n", | |
"from sklearn import metrics\n", | |
"\n", | |
"df_hitech = pd.read_csv(\"NSE-HITECHCORP.csv\")\n", | |
"df_hitech.head()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 4, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"below are the shapes: \n", | |
"(51, 8) (55, 8) (53, 8)\n" | |
] | |
} | |
], | |
"source": [ | |
"df_bhagyanar = pd.read_csv(\"NSE-BHAGYANGR.csv\")\n", | |
"\n", | |
"df_hudco = pd.read_csv(\"NSE-HUDCO.csv\")\n", | |
"\n", | |
"print('below are the shapes: ')\n", | |
"print(df_hitech.shape, df_bhagyanar.shape, df_hudco.shape)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 6, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"[ 209.1 209.95 204.1 205.8 206.7 2935. 6.09]\n" | |
] | |
} | |
], | |
"source": [ | |
"column_names = ['Open', 'High', 'Low', 'Last', 'Close', 'Total Trade Quantity', 'Turnover (Lacs)']\n", | |
"\n", | |
"X_hitech = df_hitech.loc[:, column_names].values\n", | |
"X_bhagyanagar = df_bhagyanar.loc[:, column_names].values\n", | |
"X_hudco = df_hudco.loc[:, column_names].values\n", | |
"\n", | |
"X = np.concatenate([X_hitech, X_bhagyanagar, X_hudco], axis=0)\n", | |
"\n", | |
"print(X[0])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 7, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"some samples of y\n", | |
"[1000 1000 1000 1000 1000]\n", | |
"first x shape and then y shape\n", | |
"shape of X: (159, 7)\n", | |
"shape of y: (159,)\n", | |
"[[ 209.1 209.95 204.1 205.8 206.7 2935. 6.09]\n", | |
" [ 212. 214.95 208.3 208.3 209.15 5094. 10.78]]\n", | |
"[1000 1000]\n" | |
] | |
} | |
], | |
"source": [ | |
"# print('we will define the y now')\n", | |
"\n", | |
"y = [1000] * 51 + [2000] * 55 + [3000] * 53\n", | |
"y = np.asarray(y)\n", | |
"\n", | |
"print('some samples of y')\n", | |
"print(y[:5])\n", | |
"\n", | |
"print('first x shape and then y shape')\n", | |
"\n", | |
"print('shape of X: {}'.format(X.shape))\n", | |
"print('shape of y: {}'.format(y.shape))\n", | |
"\n", | |
"print(X[:2])\n", | |
"print(y[:2])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 11, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"[ 6.83000000e+01 6.83000000e+01 6.78000000e+01 6.79000000e+01\n", | |
" 6.80000000e+01 1.43373000e+06 9.75450000e+02]\n", | |
"[ 3000. 3000. 1000. 1000. 2000.]\n", | |
"[ 225.4 231. 214. 220.7 220.65 126911. 283.93]\n", | |
"[ 1000. 1000. 1000. 1000. 3000.]\n" | |
] | |
} | |
], | |
"source": [ | |
"from sklearn.model_selection import train_test_split\n", | |
"\n", | |
"def get_train_test(X, y, test_size):\n", | |
" \"\"\"Give the train and test from X and y.\n", | |
" \n", | |
" To do this first combine the matrices, then split them in ratio of test_size then strip out the X and y components.\n", | |
" \n", | |
" \"\"\"\n", | |
" y_reshaped = np.array([y.T])\n", | |
" combined_X_y = np.concatenate((X, y_reshaped.T), axis=1)\n", | |
" combined_Xy_train, combined_Xy_test = train_test_split(combined_X_y, test_size=test_size)\n", | |
"\n", | |
" X_train, y_train_2d = np.split(combined_Xy_train, [-1], axis=1)\n", | |
" y_train = np.squeeze(y_train_2d)\n", | |
"\n", | |
" X_test, y_test_2d = np.split(combined_Xy_test, [-1], axis=1)\n", | |
" y_test = np.squeeze(y_test_2d)\n", | |
" \n", | |
" return X_train, y_train, X_test, y_test\n", | |
" \n", | |
"X_train, y_train, X_test, y_test = get_train_test(X, y, test_size=0.2)\n", | |
"\n", | |
"print(X_train[0])\n", | |
"print(y_train[:5])\n", | |
"\n", | |
"print(X_test[0])\n", | |
"print(y_test[:5])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 13, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"[ 0.05469505 0. 0.14321643 0.19745815 0.23498935 0.15445189\n", | |
" 0.21518912]\n", | |
"normal X_test predictions are below:\n", | |
"[ 1000. 1000. 1000. 1000. 3000.]\n" | |
] | |
} | |
], | |
"source": [ | |
"clf = RandomForestClassifier(max_depth=2, random_state=0)\n", | |
"clf.fit(X_train, y_train)\n", | |
"print(clf.feature_importances_)\n", | |
"\n", | |
"print('normal X_test predictions are below:')\n", | |
"\n", | |
"normal_predictions = clf.predict(X_test)\n", | |
"\n", | |
"print(normal_predictions[:5])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 14, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"NOw we will perform PCA. To do that we need to first scale the dataset\n", | |
"(127, 7)\n", | |
"mean is:\n", | |
"1.55855830679e-16\n" | |
] | |
} | |
], | |
"source": [ | |
"print(\"NOw we will perform PCA. To do that we need to first scale the dataset\")\n", | |
"from sklearn.preprocessing import StandardScaler\n", | |
"\n", | |
"X_train_scaled = StandardScaler().fit_transform(X_train)\n", | |
"X_test_scaled = StandardScaler().fit_transform(X_test)\n", | |
"\n", | |
"mu = X_train_scaled.mean()\n", | |
"\n", | |
"print(X_train_scaled.shape)\n", | |
"print('mean is:')\n", | |
"print(mu)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 15, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"explained variance in train\n", | |
"[ 5.0029508 1.98866868]\n", | |
"classified feature importances\n", | |
"[ 0.37365783 0.62634217]\n" | |
] | |
} | |
], | |
"source": [ | |
"from sklearn.decomposition import PCA\n", | |
"pca = PCA(n_components=2)\n", | |
"\n", | |
"training_features = pca.fit_transform(X_train_scaled)\n", | |
"print('explained variance in train')\n", | |
"print(pca.explained_variance_)\n", | |
"\n", | |
"clf.fit(training_features, y_train)\n", | |
"print('classified feature importances')\n", | |
"print(clf.feature_importances_)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 16, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"trying out the prediction capabilities\n", | |
"[[ 2.57645802 0.05547991]\n", | |
" [ 2.48947141 -0.02405964]]\n", | |
"explained variance in test\n", | |
"[ 5.15421156 1.83697385]\n", | |
"PCA predictions are below:\n", | |
"[ 1000. 1000. 1000. 1000. 3000.]\n" | |
] | |
} | |
], | |
"source": [ | |
"print('trying out the prediction capabilities')\n", | |
"test_features = pca.fit_transform(X_test_scaled)\n", | |
"print(test_features[:2])\n", | |
"\n", | |
"print('explained variance in test')\n", | |
"print(pca.explained_variance_)\n", | |
"\n", | |
"predictions = clf.predict(test_features)\n", | |
"\n", | |
"print('PCA predictions are below:')\n", | |
"print(predictions[:5])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 17, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"##############################################\n", | |
"normal X_test predictions are below:\n", | |
"[ 1000. 1000. 1000. 1000. 3000.]\n", | |
"......................................\n", | |
"PCA predictions are below:\n", | |
"[ 1000. 1000. 1000. 1000. 3000.]\n", | |
"here are the real values\n", | |
"[ 1000. 1000. 1000. 1000. 3000.]\n", | |
"################################################\n", | |
"what is the prediction score...\n", | |
"normal predictive score: 1.0\n", | |
"pca predictive score: 0.96875\n" | |
] | |
} | |
], | |
"source": [ | |
"print('##############################################')\n", | |
"print('normal X_test predictions are below:')\n", | |
"print(normal_predictions[:5])\n", | |
"print('......................................')\n", | |
"print('PCA predictions are below:')\n", | |
"print(predictions[:5])\n", | |
"print('here are the real values')\n", | |
"print(y_test[:5])\n", | |
"\n", | |
"print('################################################')\n", | |
"print('what is the prediction score...')\n", | |
"normal_pscore = metrics.accuracy_score(y_test, normal_predictions)\n", | |
"pca_score = metrics.accuracy_score(y_test, predictions)\n", | |
"print(\"normal predictive score: {}\".format(normal_pscore))\n", | |
"print(\"pca predictive score: {}\".format(pca_score))" | |
] | |
} | |
], | |
"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": "3.6.1" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment