mhjensen
89 lines
2.7 KiB
Plaintext
89 lines
2.7 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"<!-- dom:TITLE: Data Analysis and Machine Learning: Representing data -->\n",
|
|
"# Data Analysis and Machine Learning: Representing data\n",
|
|
"<!-- dom:AUTHOR: Morten Hjorth-Jensen at Department of Physics, University of Oslo & Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University -->\n",
|
|
"<!-- Author: --> \n",
|
|
"**Morten Hjorth-Jensen**, Department of Physics, University of Oslo and Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University\n",
|
|
"\n",
|
|
"Date: **Nov 26, 2017**\n",
|
|
"\n",
|
|
"Copyright 1999-2017, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"## Representing data, overarching aims"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {
|
|
"collapsed": false
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"%matplotlib inline\n",
|
|
"\n",
|
|
"import numpy as np\n",
|
|
"import matplotlib.pyplot as plt\n",
|
|
"from scipy import sparse\n",
|
|
"import pandas as pd\n",
|
|
"from IPython.display import display\n",
|
|
"eye = np.eye(4)\n",
|
|
"print(eye)\n",
|
|
"sparse_mtx = sparse.csr_matrix(eye)\n",
|
|
"print(sparse_mtx)\n",
|
|
"x = np.linspace(-10,10,100)\n",
|
|
"y = np.sin(x)\n",
|
|
"plt.plot(x,y,marker='x')\n",
|
|
"plt.show()\n",
|
|
"data = {'Name': [\"John\", \"Anna\", \"Peter\", \"Linda\"], 'Location': [\"Roma\", \"Napoli\", \"Torino\", \"Milano\"], 'Age':[51, 21, 34, 45]}\n",
|
|
"data_pandas = pd.DataFrame(data)\n",
|
|
"display(data_pandas)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Representing data, overarching aims"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {
|
|
"collapsed": false
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"import numpy as np\n",
|
|
"import matplotlib.pyplot as plt\n",
|
|
"from scipy import sparse\n",
|
|
"import pandas as pd\n",
|
|
"from IPython.display import display\n",
|
|
"import mglearn\n",
|
|
"import sklearn\n",
|
|
"from sklearn.linear_model import LinearRegression\n",
|
|
"from sklearn.tree import DecisionTreeRegressor\n",
|
|
"x, y = mglearn.datasets.make_wave(n_samples=100)\n",
|
|
"line = np.linspace(-3,3,1000,endpoint=False).reshape(-1,1)\n",
|
|
"reg = DecisionTreeRegressor(min_samples_split=3).fit(x,y)\n",
|
|
"plt.plot(line, reg.predict(line), label=\"decision tree\")\n",
|
|
"regline = LinearRegression().fit(x,y)\n",
|
|
"plt.plot(line, regline.predict(line), label= \"Linear Rgression\")\n",
|
|
"plt.show()"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|