lista = [1, 2, 3, 4 , 5]
lista

a = np.array(lista)
a

type(a)

a.dtype

a.ndim

a.shape

a = np.arange(10)
a

a[0], a[2], a[-1]

a[mis_indices]

a[2:9] 

a[2:9:3] 

a[::2]

a[3::2]

a[-2:]

a = np.array([1, 2, 3])
b = a[:]
b

a

fig, ax  = plt.subplots()
x = np.linspace(-5, 3, 100)
ax.plot(x, f(x));

x_min = optimize.fmin_bfgs(f, -2)
x_min

optimize.fmin_bfgs(f, 0.5) 

optimize.brent(f)

optimize.fminbound(f, -4, 2)

import pandas as pd

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

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

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

df.head(2)

df.tail(3)

df.index

df.columns

df.values

df.describe()

df.T

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

df.sort(columns='B')

type(df['A'])

df[0:3]

df['20130102':'20130104']

df.mean()

df.apply(np.cumsum)

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

pd.concat(pieces)

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()

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

import pandas as pd
import statsmodels.api as sm
import numpy as np
 
# read the data in
df = pd.read_csv("http://www.ats.ucla.edu/stat/data/binary.csv")
 
# rename the 'rank' column because there is also a DataFrame method called 'rank'
df.columns = ["admit", "gre", "gpa", "prestige"]
dummy_ranks = pd.get_dummies(df['prestige'], prefix='prestige')
dummy_ranks.head()

# create a clean data frame for the regression
cols_to_keep = ['admit', 'gre', 'gpa']
data = df[cols_to_keep].join(dummy_ranks.ix[:, 'prestige_2':])
data.head()

# manually add the intercept
data['intercept'] = 1.0

train_cols = data.columns[1:]
# Index([gre, gpa, prestige_2, prestige_3, prestige_4], dtype=object)
 
logit = sm.Logit(data['admit'], data[train_cols])
 
# fit the model
result = logit.fit()

result.summary()

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()