# As usual 
%matplotlib inline

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

s = pd.Series([1,3,5,np.nan,6,8]) # creamos una serie
s

dates = pd.date_range('20130101',periods=6)
dates

df = pd.DataFrame(np.random.randn(6,4),index=dates,columns=list('ABCD')) # creamos un dataframe

df

# creamos un df a partir de un diccionario
df2 = pd.DataFrame({ 'A' : 1.,
                     'B' : pd.Timestamp('20130102'),
                     'C' : pd.Series(1,index=range(4),dtype='float32'),
                     'D' : np.array([3] * 4,dtype='int32'),
                     'E' : 'foo' })

df2

df2.dtypes

df.head()

df.tail(3)

df.index

df.columns

df.values

df.describe

df.T

df.sort_index(axis=1, ascending=False)

df.sort(columns='B')

df['A']

df[0:3]

df['20130102':'20130104']

df.mean()

df.mean(1)

df.apply(np.cumsum)

df = pd.DataFrame(np.random.randn(10, 4))
df

pieces = [df[:3], df[3:7], df[7:]]

pd.concat(pieces)

# groupby
df = pd.DataFrame({'A' : ['foo', 'bar', 'foo', 'bar',
                         'foo', 'bar', 'foo', 'foo'],
                   'B' : ['one', 'one', 'two', 'three',
                          'two', 'two', 'one', 'three'],
                   'C' : np.random.randn(8), 
                   'D' : np.random.randn(8)})
df

df.groupby('A').sum()

In [86]: df.groupby(['A','B']).sum()

# tablas pivotantes
df = pd.DataFrame({ 'A' : ['one', 'one', 'two', 'three'] * 3,
                 'B' : ['A', 'B', 'C'] * 4,
                 'C' : ['foo', 'foo', 'foo', 'bar', 'bar', 'bar'] * 2,
                 'D' : np.random.randn(12),
                 'E' : np.random.randn(12)})
df

pd.pivot_table(df, values='D', rows=['A', 'B'], cols=['C'])

ts = pd.Series(np.random.randn(1000), index=pd.date_range('1/1/2000', periods=1000))

df = pd.DataFrame(np.random.randn(1000, 4), index=ts.index,
                  columns=['A', 'B', 'C', 'D'])
df = df.cumsum()

plt.figure(); 
df.plot(); 
plt.legend(loc='best')

import statsmodels.api as sm

nsample = 50
sig = 0.25
x1 = np.linspace(0, 20, nsample)
X = np.c_[x1, np.sin(x1), (x1-5)**2, np.ones(nsample)]
beta = [0.5, 0.5, -0.02, 5.]
y_true = np.dot(X, beta)
y = y_true + sig * np.random.normal(size=nsample)

olsmod = sm.OLS(y, X)
olsres = olsmod.fit()

print olsres.params
print olsres.bse

ypred = olsres.predict(X)

x1n = np.linspace(20.5,25, 10)
Xnew = np.c_[x1n, np.sin(x1n), (x1n-5)**2, np.ones(10)]
ynewpred =  olsres.predict(Xnew) # predict out of sample
print ypred

plt.figure()
plt.plot(x1, y, 'o', x1, y_true, 'b-')

plt.plot(np.hstack((x1, x1n)), np.hstack((ypred, ynewpred)),'r')

plt.title('OLS, azul: verdadero, rojo: valores predichos')

import numpy as np
import pylab as pl
from matplotlib.colors import ListedColormap
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import make_moons, make_circles, make_classification
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.lda import LDA
from sklearn.qda import QDA

h = .02  # step size in the mesh

names = ["Nearest Neighbors", "Linear SVM", "RBF SVM", "Decision Tree",
         "Random Forest", "Naive Bayes", "LDA", "QDA"]
classifiers = [
    KNeighborsClassifier(3),
    SVC(kernel="linear", C=0.025),
    SVC(gamma=2, C=1),
    DecisionTreeClassifier(max_depth=5),
    RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),
    GaussianNB(),
    LDA(),
    QDA()]

X, y = make_classification(n_features=2, n_redundant=0, n_informative=2,
                           random_state=1, n_clusters_per_class=1)
rng = np.random.RandomState(2)
X += 2 * rng.uniform(size=X.shape)
linearly_separable = (X, y)

datasets = [make_moons(noise=0.3, random_state=0),
            make_circles(noise=0.2, factor=0.5, random_state=1),
            linearly_separable
            ]

figure = pl.figure(figsize=(24, 8))
i = 1
# iterate over datasets
for ds in datasets:
    # preprocess dataset, split into training and test part
    X, y = ds
    X = StandardScaler().fit_transform(X)
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.4)

    x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
    y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
                         np.arange(y_min, y_max, h))

    # just plot the dataset first
    cm = pl.cm.RdBu
    cm_bright = ListedColormap(['#FF0000', '#0000FF'])
    ax = pl.subplot(len(datasets), len(classifiers) + 1, i)
    # Plot the training points
    ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright)
    # and testing points
    ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6)
    ax.set_xlim(xx.min(), xx.max())
    ax.set_ylim(yy.min(), yy.max())
    ax.set_xticks(())
    ax.set_yticks(())
    i += 1

    # iterate over classifiers
    for name, clf in zip(names, classifiers):
        ax = pl.subplot(len(datasets), len(classifiers) + 1, i)
        clf.fit(X_train, y_train)
        score = clf.score(X_test, y_test)

        # Plot the decision boundary. For that, we will asign a color to each
        # point in the mesh [x_min, m_max]x[y_min, y_max].
        if hasattr(clf, "decision_function"):
            Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
        else:
            Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]

        # Put the result into a color plot
        Z = Z.reshape(xx.shape)
        ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)

        # Plot also the training points
        ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright)
        # and testing points
        ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright,
                   alpha=0.6)

        ax.set_xlim(xx.min(), xx.max())
        ax.set_ylim(yy.min(), yy.max())
        ax.set_xticks(())
        ax.set_yticks(())
        ax.set_title(name)
        ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'),
                size=15, horizontalalignment='right')
        i += 1

figure.subplots_adjust(left=.02, right=.98)
pl.show()