noah/QM-7063-Learning-Practice-8
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Compare commits

base: noah:25105820877e3f6a2380d05352588858f7170c47
Branches Tags
noah:main
..
compare: noah:faa108bc90b4f246c43f30bc4cf1f773f3f893db
Branches Tags
noah:main

No commits in common. "25105820877e3f6a2380d05352588858f7170c47" and "faa108bc90b4f246c43f30bc4cf1f773f3f893db" have entirely different histories.
2510582087 ... faa108bc90

1 changed files with 16 additions and 125 deletions
Show Stats Expand all files Collapse all files

141
Schrick-Noah_Learning-Practice-8.ipynb
View File

@ -14,7 +14,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 16, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -27,15 +27,12 @@
"import pandas as pd\n", "import pandas as pd\n",
"from sklearn.model_selection import train_test_split\n", "from sklearn.model_selection import train_test_split\n",
"from sklearn.naive_bayes import MultinomialNB\n", "from sklearn.naive_bayes import MultinomialNB\n",
"from sklearn.metrics import mean_squared_error\n",
"from math import sqrt\n",
"\n",
"import matplotlib.pylab as plt\n", "import matplotlib.pylab as plt\n",
"from dmba import classificationSummary, gainsChart\n", "from dmba import classificationSummary, gainsChart\n",
"\n", "\n",
"from sklearn import preprocessing\n", "from sklearn import preprocessing\n",
"from sklearn.metrics import accuracy_score\n", "from sklearn.metrics import accuracy_score\n",
"from sklearn.neighbors import NearestNeighbors, KNeighborsClassifier, KNeighborsRegressor" "from sklearn.neighbors import NearestNeighbors, KNeighborsClassifier"
] ]
}, },
{ {
@ -52,13 +49,11 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 64, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# Pre-processing\n", "# Pre-processing"
"housing_df = pd.read_csv('BostonHousing.csv')\n",
"trainData, validData = train_test_split(housing_df, test_size=0.4, random_state=26)"
] ]
}, },
{ {
@ -72,72 +67,11 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 68, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# a\n", "# a"
"## Normalize\n",
"scaler = preprocessing.StandardScaler()\n",
"\n",
"predictors = housing_df.columns.values.tolist()\n",
"predictors.remove('CAT. MEDV')\n",
"predictors.remove('MEDV')\n",
"\n",
"scaler.fit(trainData[predictors]) # Note the use of an array of column names\n",
"\n",
"# Transform the full dataset\n",
"housingNorm = pd.concat([pd.DataFrame(scaler.transform(housing_df[predictors]), \n",
" columns=predictors),\n",
" housing_df[['MEDV']]], axis=1)\n",
"\n",
"trainNorm = housingNorm.iloc[trainData.index]\n",
"validNorm = housingNorm.iloc[validData.index]\n",
"#newHousingNorm = pd.DataFrame(scaler.transform(housingNorm), columns=predictors)"
]
},
{
"cell_type": "code",
"execution_count": 69,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" k accuracy\n",
"0 1 0.643141\n",
"1 2 0.720241\n",
"2 3 0.710570\n",
"3 4 0.676896\n"
]
}
],
"source": [
"## K-NN\n",
"results = []\n",
"train_X = trainNorm[predictors]\n",
"train_y = trainNorm['MEDV']\n",
"valid_X = validNorm[predictors]\n",
"valid_y = validNorm['MEDV']\n",
"\n",
"for k in range(1,5):\n",
" knn = KNeighborsRegressor(n_neighbors=k).fit(train_X, train_y)\n",
" results.append({\n",
" 'k': k,\n",
" 'accuracy': knn.score(valid_X, valid_y)\n",
" })\n",
"\n",
"# Convert results to a pandas data frame\n",
"results = pd.DataFrame(results)\n",
"print(results)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The best k is k=2. This means we have greater accuracy when each point has its nearest 2 neighbors identified."
] ]
}, },
{ {
@ -153,33 +87,11 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 73, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [],
{
"name": "stdout",
"output_type": "stream",
"text": [
"[19.45]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/noah/.local/lib/python3.10/site-packages/sklearn/base.py:420: UserWarning: X does not have valid feature names, but StandardScaler was fitted with feature names\n",
" warnings.warn(\n",
"/home/noah/.local/lib/python3.10/site-packages/sklearn/base.py:420: UserWarning: X does not have valid feature names, but KNeighborsRegressor was fitted with feature names\n",
" warnings.warn(\n"
]
}
],
"source": [ "source": [
"# b\n", "# b"
"sample = [[0.2, 0, 7, 0, 0.538, 6, 62, 4.7, 4, 307, 21, 10]]\n",
"sample_norm = scaler.transform(sample)\n",
"ans_b = knn.predict(sample_norm)\n",
"print(ans_b)"
] ]
}, },
{ {
@ -192,11 +104,12 @@
] ]
}, },
{ {
"attachments": {}, "cell_type": "code",
"cell_type": "markdown", "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [],
"source": [ "source": [
"Error will be zero, or close to zero. Since the training data was used to build the model, checking the training data against itself should yield very high accuracy." "# c"
] ]
}, },
{ {
@ -213,8 +126,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# d.\n", "# d."
"This model was built and tuned with a specific k value (k=2). This value of k was the best for the data used, but does not mean that this value of k is the best for future data."
] ]
}, },
{ {
@ -231,14 +143,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# e.\n", "# e."
"\n",
"1. Select k-nearest samples\n",
"2. Compute average value for k-nearest neighbors\n",
"3. Score value with new data\n",
"4. Repeat for all new data samples\n",
"\n",
"If there are several thousands of new tracts, then k-NN will take much longer to run. The model will need to be rebuilt numerous times over the several thousand pieces of data. The lack of scalability will be a disadvantage. "
] ]
}, },
{ {
@ -483,22 +388,8 @@
} }
], ],
"metadata": { "metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": { "language_info": {
"codemirror_mode": { "name": "python"
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.10"
}, },
"orig_nbformat": 4 "orig_nbformat": 4
}, },