diff --git a/doc/pub/How2ReadData/html/._How2ReadData-bs000.html b/doc/pub/How2ReadData/html/._How2ReadData-bs000.html index 5719cc4c0..eb14f46f6 100644 --- a/doc/pub/How2ReadData/html/._How2ReadData-bs000.html +++ b/doc/pub/How2ReadData/html/._How2ReadData-bs000.html @@ -40,7 +40,8 @@ Automatically generated HTML file from DocOnce source @@ -63,6 +64,7 @@ end of tocinfo --> Contents @@ -112,6 +114,7 @@ end of tocinfo --> diff --git a/doc/pub/How2ReadData/html/._How2ReadData-bs001.html b/doc/pub/How2ReadData/html/._How2ReadData-bs001.html index 93528e2d8..774e3f2ac 100644 --- a/doc/pub/How2ReadData/html/._How2ReadData-bs001.html +++ b/doc/pub/How2ReadData/html/._How2ReadData-bs001.html @@ -40,7 +40,8 @@ Automatically generated HTML file from DocOnce source @@ -63,6 +64,7 @@ end of tocinfo --> Contents @@ -82,18 +84,40 @@ end of tocinfo -->

+

+ +

import numpy as np
+import matplotlib.pyplot as plt
+from scipy import sparse
+import pandas as pd
+from IPython.display import display
+eye = np.eye(4)
+print(eye)
+sparse_mtx = sparse.csr_matrix(eye)
+print(sparse_mtx)
+x = np.linspace(-10,10,100)
+y = np.sin(x)
+plt.plot(x,y,marker='x')
+plt.show()
+data = {'Name': ["John", "Anna", "Peter", "Linda"], 'Location': ["Roma", "Napoli", "Torino", "Milano"], 'Age':[51, 21, 34, 45]}
+data_pandas = pd.DataFrame(data)
+display(data_pandas)
+

+

diff --git a/doc/pub/How2ReadData/html/How2ReadData-bs.html b/doc/pub/How2ReadData/html/How2ReadData-bs.html index 5719cc4c0..eb14f46f6 100644 --- a/doc/pub/How2ReadData/html/How2ReadData-bs.html +++ b/doc/pub/How2ReadData/html/How2ReadData-bs.html @@ -40,7 +40,8 @@ Automatically generated HTML file from DocOnce source @@ -63,6 +64,7 @@ end of tocinfo --> Contents @@ -112,6 +114,7 @@ end of tocinfo --> diff --git a/doc/pub/How2ReadData/html/How2ReadData-reveal.html b/doc/pub/How2ReadData/html/How2ReadData-reveal.html index c5132d2f5..234d4cb92 100644 --- a/doc/pub/How2ReadData/html/How2ReadData-reveal.html +++ b/doc/pub/How2ReadData/html/How2ReadData-reveal.html @@ -147,6 +147,55 @@ td.padding {

+ + +

import numpy as np
+import matplotlib.pyplot as plt
+from scipy import sparse
+import pandas as pd
+from IPython.display import display
+eye = np.eye(4)
+print(eye)
+sparse_mtx = sparse.csr_matrix(eye)
+print(sparse_mtx)
+x = np.linspace(-10,10,100)
+y = np.sin(x)
+plt.plot(x,y,marker='x')
+plt.show()
+data = {'Name': ["John", "Anna", "Peter", "Linda"], 'Location': ["Roma", "Napoli", "Torino", "Milano"], 'Age':[51, 21, 34, 45]}
+data_pandas = pd.DataFrame(data)
+display(data_pandas)
+
+ +
+ + + +
+

Representing data, overarching aims

+
+ +

+ + +

import numpy as np
+import matplotlib.pyplot as plt
+from scipy import sparse
+import pandas as pd
+from IPython.display import display
+import mglearn
+import sklearn
+from sklearn.linear_model import LinearRegression
+from sklearn.tree import DecisionTreeRegressor
+x, y = mglearn.datasets.make_wave(n_samples=100)
+line = np.linspace(-3,3,1000,endpoint=False).reshape(-1,1)
+reg = DecisionTreeRegressor(min_samples_split=3).fit(x,y)
+plt.plot(line, reg.predict(line), label="decision tree")
+regline = LinearRegression().fit(x,y)
+plt.plot(line, regline.predict(line), label= "Linear Rgression")
+plt.show()
+
+
diff --git a/doc/pub/How2ReadData/html/How2ReadData-solarized.html b/doc/pub/How2ReadData/html/How2ReadData-solarized.html index be536b297..2b0f5ca82 100644 --- a/doc/pub/How2ReadData/html/How2ReadData-solarized.html +++ b/doc/pub/How2ReadData/html/How2ReadData-solarized.html @@ -60,7 +60,8 @@ div { text-align: justify; text-justify: inter-word; } @@ -95,7 +96,57 @@ end of tocinfo -->

+

+ +

import numpy as np
+import matplotlib.pyplot as plt
+from scipy import sparse
+import pandas as pd
+from IPython.display import display
+eye = np.eye(4)
+print(eye)
+sparse_mtx = sparse.csr_matrix(eye)
+print(sparse_mtx)
+x = np.linspace(-10,10,100)
+y = np.sin(x)
+plt.plot(x,y,marker='x')
+plt.show()
+data = {'Name': ["John", "Anna", "Peter", "Linda"], 'Location': ["Roma", "Napoli", "Torino", "Milano"], 'Age':[51, 21, 34, 45]}
+data_pandas = pd.DataFrame(data)
+display(data_pandas)
+
+ +
+ + +

+









+ +

Representing data, overarching aims

+
+ +

+

+ + +

import numpy as np
+import matplotlib.pyplot as plt
+from scipy import sparse
+import pandas as pd
+from IPython.display import display
+import mglearn
+import sklearn
+from sklearn.linear_model import LinearRegression
+from sklearn.tree import DecisionTreeRegressor
+x, y = mglearn.datasets.make_wave(n_samples=100)
+line = np.linspace(-3,3,1000,endpoint=False).reshape(-1,1)
+reg = DecisionTreeRegressor(min_samples_split=3).fit(x,y)
+plt.plot(line, reg.predict(line), label="decision tree")
+regline = LinearRegression().fit(x,y)
+plt.plot(line, regline.predict(line), label= "Linear Rgression")
+plt.show()
+
diff --git a/doc/pub/How2ReadData/html/How2ReadData.html b/doc/pub/How2ReadData/html/How2ReadData.html index 1dbb39e6f..2688b53b1 100644 --- a/doc/pub/How2ReadData/html/How2ReadData.html +++ b/doc/pub/How2ReadData/html/How2ReadData.html @@ -65,7 +65,8 @@ div { text-align: justify; text-justify: inter-word; } @@ -100,7 +101,57 @@ end of tocinfo -->

+

+ +

import numpy as np
+import matplotlib.pyplot as plt
+from scipy import sparse
+import pandas as pd
+from IPython.display import display
+eye = np.eye(4)
+print(eye)
+sparse_mtx = sparse.csr_matrix(eye)
+print(sparse_mtx)
+x = np.linspace(-10,10,100)
+y = np.sin(x)
+plt.plot(x,y,marker='x')
+plt.show()
+data = {'Name': ["John", "Anna", "Peter", "Linda"], 'Location': ["Roma", "Napoli", "Torino", "Milano"], 'Age':[51, 21, 34, 45]}
+data_pandas = pd.DataFrame(data)
+display(data_pandas)
+
+ +
+ + +

+









+ +

Representing data, overarching aims

+
+ +

+

+ + +

import numpy as np
+import matplotlib.pyplot as plt
+from scipy import sparse
+import pandas as pd
+from IPython.display import display
+import mglearn
+import sklearn
+from sklearn.linear_model import LinearRegression
+from sklearn.tree import DecisionTreeRegressor
+x, y = mglearn.datasets.make_wave(n_samples=100)
+line = np.linspace(-3,3,1000,endpoint=False).reshape(-1,1)
+reg = DecisionTreeRegressor(min_samples_split=3).fit(x,y)
+plt.plot(line, reg.predict(line), label="decision tree")
+regline = LinearRegression().fit(x,y)
+plt.plot(line, regline.predict(line), label= "Linear Rgression")
+plt.show()
+
diff --git a/doc/pub/How2ReadData/ipynb/How2ReadData.ipynb b/doc/pub/How2ReadData/ipynb/How2ReadData.ipynb new file mode 100644 index 000000000..bd86ecf96 --- /dev/null +++ b/doc/pub/How2ReadData/ipynb/How2ReadData.ipynb @@ -0,0 +1,88 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "\n", + "# Data Analysis and Machine Learning: Representing data\n", + "\n", + " \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 +} diff --git a/doc/pub/How2ReadData/ipynb/ipynb-How2ReadData-src.tar.gz b/doc/pub/How2ReadData/ipynb/ipynb-How2ReadData-src.tar.gz index 7a00fedb1..52374d85e 100644 Binary files a/doc/pub/How2ReadData/ipynb/ipynb-How2ReadData-src.tar.gz and b/doc/pub/How2ReadData/ipynb/ipynb-How2ReadData-src.tar.gz differ diff --git a/doc/pub/How2ReadData/pdf/How2ReadData-beamer-handouts2x3.pdf b/doc/pub/How2ReadData/pdf/How2ReadData-beamer-handouts2x3.pdf index 071238a54..9e3bf4188 100644 Binary files a/doc/pub/How2ReadData/pdf/How2ReadData-beamer-handouts2x3.pdf and b/doc/pub/How2ReadData/pdf/How2ReadData-beamer-handouts2x3.pdf differ diff --git a/doc/pub/How2ReadData/pdf/How2ReadData-beamer.pdf b/doc/pub/How2ReadData/pdf/How2ReadData-beamer.pdf index c3b2e42ba..e449058b6 100644 Binary files a/doc/pub/How2ReadData/pdf/How2ReadData-beamer.pdf and b/doc/pub/How2ReadData/pdf/How2ReadData-beamer.pdf differ diff --git a/doc/pub/How2ReadData/pdf/How2ReadData-minted.pdf b/doc/pub/How2ReadData/pdf/How2ReadData-minted.pdf index e1c3e94ef..05b3cb5b2 100644 Binary files a/doc/pub/How2ReadData/pdf/How2ReadData-minted.pdf and b/doc/pub/How2ReadData/pdf/How2ReadData-minted.pdf differ diff --git a/doc/src/How2ReadData/How2ReadData.do.txt b/doc/src/How2ReadData/How2ReadData.do.txt index 8cc5e3abd..f5594dfa2 100644 --- a/doc/src/How2ReadData/How2ReadData.do.txt +++ b/doc/src/How2ReadData/How2ReadData.do.txt @@ -6,6 +6,48 @@ DATE: today !split ===== Representing data, overarching aims ===== !bblock - +!bc pycod +import numpy as np +import matplotlib.pyplot as plt +from scipy import sparse +import pandas as pd +from IPython.display import display +eye = np.eye(4) +print(eye) +sparse_mtx = sparse.csr_matrix(eye) +print(sparse_mtx) +x = np.linspace(-10,10,100) +y = np.sin(x) +plt.plot(x,y,marker='x') +plt.show() +data = {'Name': ["John", "Anna", "Peter", "Linda"], 'Location': ["Roma", "Napoli", "Torino", "Milano"], 'Age':[51, 21, 34, 45]} +data_pandas = pd.DataFrame(data) +display(data_pandas) +!ec +!eblock + + + +!split +===== Representing data, overarching aims ===== +!bblock +!bc pycod +import numpy as np +import matplotlib.pyplot as plt +from scipy import sparse +import pandas as pd +from IPython.display import display +import mglearn +import sklearn +from sklearn.linear_model import LinearRegression +from sklearn.tree import DecisionTreeRegressor +x, y = mglearn.datasets.make_wave(n_samples=100) +line = np.linspace(-3,3,1000,endpoint=False).reshape(-1,1) +reg = DecisionTreeRegressor(min_samples_split=3).fit(x,y) +plt.plot(line, reg.predict(line), label="decision tree") +regline = LinearRegression().fit(x,y) +plt.plot(line, regline.predict(line), label= "Linear Rgression") +plt.show() +!ec !eblock diff --git a/doc/src/How2ReadData/make.sh b/doc/src/How2ReadData/make.sh index 0671a98d3..edfed7c87 100755 --- a/doc/src/How2ReadData/make.sh +++ b/doc/src/How2ReadData/make.sh @@ -47,7 +47,7 @@ system doconce format html $name --html_style=bootstrap --pygments_html_style=de system doconce split_html $html.html --method=split --pagination --nav_button=bottom # IPython notebook -#system doconce format ipynb $name $opt +system doconce format ipynb $name $opt # LaTeX Beamer slides beamertheme=red_plain