Update on r codes

doc/src/How2ReadData/How2ReadData.do.txt

@@ -112,9 +112,11 @@ either Python or C++ as programming languages.
 To add more entropy, _cython_ can also be used when running your notebooks. It means that Python with the Jupyter/IPython notebook 
 setup allows you to integrate widely popular softwares and tools for scientific computing. With its versatility, 
 including symbolic operations, Python offers a unique computational environment. Your Jupyter/IPython notebook 
-can easily be converted into a nicely rendered _PDF_ file or a Latex file for further processing.
+can easily be converted into a nicely rendered _PDF_ file or a Latex file for further processing. For example, convert to latex as
+!bc pycod
+jupyter nbconvert filename.ipynb --to latex
+!ec
 
-This never ends.
 If you use the light mark-up language _doconce_ you can convert a standard ascii text file into various HTML 
 formats, ipython notebooks, latex files, pdf files etc. 
 
@@ -445,7 +447,7 @@ plt.show()
 !split
 ===== Linear Least squares in R  =====
 !bblock
-!bc pycod
+!bc r
 HudsonBay = read.csv("src/Hudson_Bay.csv",header=T)
 fix(HudsonBay)
 dim(HudsonBay)
@@ -471,7 +473,7 @@ predict(linearMod,data.frame(Year=c(1910,1914,1920)),interval="confidence")
 !split
 ===== Non-Linear Least squares in R  =====
 !bblock
-!bc pycod
+!bc r
 set.seed(1485)
 len = 24
 x = runif(len)

doc/src/How2ReadData/knn.py

@@ -0,0 +1,38 @@
+import numpy as np
+import matplotlib.pyplot as plt
+from IPython.display import display
+import sklearn
+from sklearn.linear_model import LinearRegression
+from sklearn.tree import DecisionTreeRegressor
+from sklearn.model_selection import train_test_split
+import mglearn
+X, y = mglearn.datasets.make_forge()
+X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
+from sklearn.neighbors import KNeighborsClassifier
+clf = KNeighborsClassifier(n_neighbors=3)
+clf.fit(X_train, y_train)
+KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',metric_params=None, n_jobs=1, n_neighbors=3, p=2,weights='uniform')
+
+clf.predict(X_test)
+
+clf.score(X_test, y_test)
+fig, axes = plt.subplots(1, 3, figsize=(10, 3))
+for n_neighbors, ax in zip([1, 3, 9], axes):
+        clf = KNeighborsClassifier(n_neighbors=n_neighbors).fit(X, y)
+        mglearn.plots.plot_2d_separator(clf, X, fill=True, eps=0.5, ax=ax, alpha=.4)
+        ax.scatter(X[:, 0], X[:, 1], c=y, s=60, cmap=mglearn.cm2)
+        ax.set_title("%d neighbor(s)" % n_neighbors)
+
+
+data = np.loadtxt('src/Hudson_Bay.csv', delimiter=',', skiprows=1)
+x = data[:,0]
+y = data[:,1]
+#x_train,  y_train = train_test_split(x, y, random_state=0)
+line = np.linspace(1900,1930,1000,endpoint=False).reshape(-1,1)
+reg = DecisionTreeRegressor(min_samples_split=3).fit(x.reshape(-1,1),y.reshape(-1,1))
+plt.plot(line, reg.predict(line), label="decision tree")
+regline = LinearRegression().fit(x.reshape(-1,1),y.reshape(-1,1))
+plt.plot(line, regline.predict(line), label= "Linear Regression")
+plt.plot(x, y, label= "Linear Regression")
+plt.show()
+

doc/src/How2ReadData/panda.py

@@ -0,0 +1,10 @@
+import numpy as np
+import matplotlib.pyplot as plt
+from IPython.display import display
+import pandas as pd
+
+data = pd.read_csv('src/Hudson_Bay.csv', delimiter=',', skiprows=1)
+
+
+data_pandas = pd.DataFrame(data)
+display(data_pandas)

doc/src/How2ReadData/test.py

@@ -5,12 +5,29 @@ import sklearn
 from sklearn.linear_model import LinearRegression
 from sklearn.tree import DecisionTreeRegressor
 from sklearn.model_selection import train_test_split
-X_train, X_test, y_train, y_test = train_test_split(x, y, random_state=0)
+import mglearn
+X, y = mglearn.datasets.make_forge()
+X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
+from sklearn.neighbors import KNeighborsClassifier
+clf = KNeighborsClassifier(n_neighbors=3)
+clf.fit(X_train, y_train)
+KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',metric_params=None, n_jobs=1, n_neighbors=3, p=2,weights='uniform')
+
+clf.predict(X_test)
+
+clf.score(X_test, y_test)
+fig, axes = plt.subplots(1, 3, figsize=(10, 3))
+for n_neighbors, ax in zip([1, 3, 9], axes):
+        clf = KNeighborsClassifier(n_neighbors=n_neighbors).fit(X, y)
+        mglearn.plots.plot_2d_separator(clf, X, fill=True, eps=0.5, ax=ax, alpha=.4)
+        ax.scatter(X[:, 0], X[:, 1], c=y, s=60, cmap=mglearn.cm2)
+        ax.set_title("%d neighbor(s)" % n_neighbors)
+
 
 data = np.loadtxt('src/Hudson_Bay.csv', delimiter=',', skiprows=1)
 x = data[:,0]
 y = data[:,1]
-x_train,  y_train = train_test_split(x, y, random_state=0)
+#x_train,  y_train = train_test_split(x, y, random_state=0)
 line = np.linspace(1900,1930,1000,endpoint=False).reshape(-1,1)
 reg = DecisionTreeRegressor(min_samples_split=3).fit(x.reshape(-1,1),y.reshape(-1,1))
 plt.plot(line, reg.predict(line), label="decision tree")