import scipy.sparse as sparse

matrixA = sparse.lil_matrix((6,6))

matrixA = sparse.lil_matrix([

        [0,25,26,0,0,0],

        [0,0,85,5,10,0],

        [26,85,0,0,0,10],

        [0,0,0,0,0,11],

        [0,0,0,9,0,88],

        [0,0,0,11,88,0]

        ])

print matrixA

  (0, 1)        25

  (0, 2)        26

  (1, 2)        85

  (1, 3)        5

  (1, 4)        10

  (2, 0)        26

  (2, 1)        85

  (2, 5)        10

  (3, 5)        11

  (4, 3)        9

  (4, 5)        88

  (5, 3)        11

  (5, 4)        88

conda install -c vtraag python-igraph

import igraph

vertices = ["A", "B", "C", "D", "E"]

edges = [(0,1),(1,2),(2,3),(3,4),(4,5),(5,6),(6,7),(7,1),

         (1,8),  (8,2),(2,4),(4,9),(9,5),(5,7),(7,0)]

graphStyle = { 'vertex_size': 20}

g = igraph.Graph(vertex_attrs={"label": vertices}, edges=edges, directed=True)

g.write_svg("simple_star.svg", width=500, height=300, **graphStyle)

from igraph import read  

g=read("Ragusa18.net",format="pajek")  

g.vs["color"]="#3d679d" 

g.es["color"]="red" 

graphStyle={ 'vertex_size': 12, 'margin': 6} 

#graphStyle["layout"]=g.layout("fr")  # optional

g.write_svg("ragusa_graph.svg", width=600, height=600,**graphStyle)

graphStyle["layout"]=g.layout("circle")

import matplotlib.pyplot as plt

import pylab

from pylab import rcParams

import networkx as nx

# set the graph display size as 10 by 10 inches

rcParams['figure.figsize'] = 10, 10

G = nx.DiGraph()

# Add the edges and weights

G.add_edges_from([('K', 'I'),('R','T'),('V','T')], weight=3)

G.add_edges_from([('T','K'),('T','H'),('T','H')], weight=4)

# these values to determine node colors

val_map = {'K': 1.5, 'I': 0.9, 'R': 0.6, 'T': 0.2}

values = [val_map.get(node, 1.0) for node in G.nodes()]

edge_labels=dict([((u,v,),d['weight'])

                 for u,v,d in G.edges(data=True)])

#set edge colors

red_edges = [('R','T'),('T','K')]

edge_colors = ['green' if not edge in red_edges else 'red' for edge in G.edges()]

pos=nx.spring_layout(G)

nx.draw_networkx_edges(G,pos,width=2.0,alpha=0.65)

nx.draw_networkx_edge_labels(G,pos,edge_labels=edge_labels)

nx.draw(G,pos, node_color = values, node_size=1500,

 edge_color=edge_colors, edge_cmap=plt.cm.Reds)

pylab.show()

nx.is_directed_acyclic_graph(G) 

import networkx as nx

g = nx.Graph()

g.add_edge('m','i',weight=0.1)

g.add_edge('i','a',weight=1.5)

g.add_edge('m','a',weight=1.0)

g.add_edge('a','e',weight=0.75)

g.add_edge('e','h',weight=1.5) 

g.add_edge('a','h',weight=2.2)

nx.draw(g)

print nx.shortest_path(g,'i','h')

['i', 'a', 'h']

conda install -c conda-forge textblob

python -m textblob.download_corpora

from textblob.classifiers import NaiveBayesClassifier

from textblob.blob import TextBlob

train = [

    ('I like this new tv show.', 'pos'),

    ('This is a very exciting event!', 'pos'),

    ('I feel very good about after I workout.', 'pos'),

    ('This is my most accomplished work.', 'pos'),

    ("What an awesome country", 'pos'),

    ("They have horrible service", 'neg'),

    ('I do not like this new restaurant', 'neg'),

    ('I am tired of waiting for my new book.', 'neg'),

    ("I can't deal with my toothache", 'neg'),

    ("The fun events in costa rica were amazing",'pos'), 

    ('He is my worst boss!', 'neg'),

    ('People do have bad writing skills on facebook', 'neg')

]

test = [

    ('The beer was good.', 'pos'),

    ('I do not enjoy my job', 'neg'),

    ("I feel amazing!", 'pos'),

    ('Mark is a friend of mine.', 'pos'),

    ("I can't believe I was asked to do this.", 'neg')

]

cl = NaiveBayesClassifier(train)

print(cl.classify("The new movie was amazing."))  # "pos"

print(cl.classify("I don't like ther noodles."))   # "neg"

print "Test Results"

cl.update(test)

# Classify a TextBlob

blob = TextBlob("The food was good. But the service was horrible. "

                "My father was not pleased.", classifier=cl)

print(blob)

print(blob.classify())

for sentence in blob.sentences:

    print(sentence)

    print(sentence.classify())

# Compute accuracy

print("Accuracy: {0}".format(cl.accuracy(test)))

# Show 5 most informative features

cl.show_informative_features(10)

import csv

import matplotlib.pyplot as plt

count=0

x=[]

y=[]

z=[]

with open('./fruits_data.csv', 'r') as csvf:

  reader = csv.reader(csvf, delimiter=',')

  for row in reader:

    if count > 0:

      x.append(row[0])

      y.append(row[1])

      if ( row[2] == 'Apple' ): z.append('r')

      elif ( row[2] == 'Pear' ): z.append('g')

      else: z.append('y')

    count += 1

plt.figure(figsize=(11,11))

recs=[]

classes=['Apples', 'Pear', 'Bananas']

class_colours = ['r','g','y']

plt.title("Apples, Bananas and Pear by Weight and Shape", fontsize=18)

plt.xlabel("Shape category number", fontsize=14)

plt.ylabel("Weight in ounces", fontsize=14)

plt.scatter(x,y,s=600,c=z)

from math import pow, sqrt

dist=[]

def determineFruit(xv, yv, threshold_radius):

  for i in range(1,len(x)):

    xdif=pow(float(x[i])-xv, 2)

    ydif=pow(float(y[i])-yv, 2)

    sqrtdist = sqrt(xdif+ydif)

    if ( xdif < threshold_radius and 

         ydif < threshold_radius and sqrtdist < threshold_radius):

      dist.append(sqrtdist)

    else:

      dist.append(99)

  pear_count=0

  apple_count=0

  banana_count=0

  for i in range(1,len(dist)):

      if dist[i] < threshold_radius:

        if z[i] == 'g': pear_count += 1

        if z[i] == 'r': apple_count += 1

        if z[i] == 'y': banana_count += 1

  if ( apple_count >= pear_count and apple_count >= banana_count ):

    return "apple"

  elif ( pear_count >= apple_count and pear_count >= banana_count):

    return "pear"

  elif ( banana_count >= apple_count and banana_count >= pear_count):

    return "banana"

dist=[]

determine = determineFruit(3.5,6.2, 1)

print determine

banana

import numpy as np

import pandas as pd

import sklearn.linear_model as lm

import sklearn.cross_validation as cv

import matplotlib.pyplot as plt

train = pd.read_csv('./titanic_train.csv')

test = pd.read_csv('./titanic_test.csv')

train[train.columns[[2,4,5,1]]].head()

   Pclass     Sex   Age  Survived

0       3    male  22.0         0

1       1  female  38.0         1

2       3  female  26.0         1

3       1  female  35.0         1

4       3    male  35.0         0

data = train[['Sex', 'Age', 'Pclass', 'Survived']].copy()

data['Sex'] = data['Sex'] == 'female'

data = data.dropna()

data_np = data.astype(np.int32).values

X = data_np[:,:-1]

y = data_np[:,-1]

female = X[:,0] == 1

survived = y == 1

# This vector contains the age of the passengers.

age = X[:,1]

# We compute a few histograms.

bins_ = np.arange(0, 121, 5)

S = {'male': np.histogram(age[survived & ~female], 

                          bins=bins_)[0],

     'female': np.histogram(age[survived & female], 

                            bins=bins_)[0]}

D = {'male': np.histogram(age[~survived & ~female], 

                          bins=bins_)[0],

     'female': np.histogram(age[~survived & female], 

                            bins=bins_)[0]}

bins = bins_[:-1]

plt.figure(figsize=(15,8))

for i, sex, color in zip((0, 1),('male', 'female'), ('#3345d0', '#cc3dc0')):

    plt.subplot(121 + i)

    plt.bar(bins, S[sex], bottom=D[sex], color=color,

            width=5, label='Survived')

    plt.bar(bins, D[sex], color='#aaaaff', width=5, label='Died', alpha=0.4)

    plt.xlim(0, 80)

    plt.grid(None)

    plt.title(sex + " Survived")

    plt.xlabel("Age (years)")

    plt.legend()

(X_train, X_test, y_train, y_test) = cv.train_test_split(X, y, test_size=.05)

print X_train, y_train

# Logistic Regression from linear_model

logreg = lm.LogisticRegression();

logreg.fit(X_train, y_train)

y_predicted = logreg.predict(X_test)

plt.figure(figsize=(15,8));

plt.imshow(np.vstack((y_test, y_predicted)),

           interpolation='none', cmap='bone');

plt.xticks([]); plt.yticks([]);

plt.title(("Actual and predicted survival outcomes on the test set"))

logreg.coef_

array([[ 2.40922883, -0.03177726, -1.13610297]])

import matplotlib.pyplot as plt

from sklearn.cluster import KMeans

import csv

x=[]

y=[]

with open('./cluster_input.csv', 'r') as csvf:

  reader = csv.reader(csvf, delimiter=',')

  for row in reader:

      x.append(float(row[0]))

      y.append(float(row[1]))

data=[]

for i in range(0,120):

  data.append([x[i],y[i]])

plt.figure(figsize=(10,10))

plt.xlim(0,12)

plt.ylim(0,12)

plt.xlabel("X values",fontsize=14)

plt.ylabel("Y values", fontsize=14)

plt.title("Before Clustering ", fontsize=20)

plt.plot(x, y, 'k.', color='#0080ff', markersize=35, alpha=0.6)

kmeans = KMeans(init='k-means++', n_clusters=3, n_init=10)

kmeans.fit(data)

plt.figure(figsize=(10,10))

plt.xlim(0,12)

plt.ylim(0,12)

plt.xlabel("X values",fontsize=14)

plt.ylabel("Y values", fontsize=14)

plt.title("After K-Means Clustering (from scikit-learn)", fontsize=20)

plt.plot(x, y, 'k.', color='#ffaaaa', markersize=45, alpha=0.6)

# Plot the centroids as a blue X

centroids = kmeans.cluster_centers_

plt.scatter(centroids[:, 0], centroids[:, 1], marker='x', s=200,

  linewidths=3, color='b', zorder=10)

plt.show()

import numpy as np

import matplotlib.pyplot as plt

from scipy import stats

from sklearn.linear_model import BayesianRidge

np.random.seed(0)

n_samples, n_features = 200, 200

X = np.random.randn(n_samples, n_features) # 가우시안 데이터

# 정밀도 4로 가중치를 만듦

theta = 4.

w = np.zeros(n_features)

# 관심 있는 8개의 가중치만 유지

relevant_features = np.random.randint(0, n_features, 8)

for i in relevant_features :

    w[i] = stats.norm.rvs(loc=0, scale=1. / np.sqrt(theta))

alpha_ = 50.

noise = stats.norm.rvs(loc=0, scale=1. / np.sqrt(alpha_), size=n_samples)

y = np.dot(X, w) + noise

# 베이즈 능형 회귀 (Bayesian Ridge Regression) 에 맞춤

clf = BayesianRidge(compute_score=True)

clf.fit(X, y)

# 가중치, 예측 및 히스토그램 가중치를 시각화

plt.figure(figsize=(11, 10))

plt.title("Weights of the model", fontsize=18)

plt.plot(clf.coef_, 'b-', label="Bayesian Ridge estimate")

plt.plot(w, 'g-', label="Training Set Accuracy")

plt.xlabel("Features", fontsize=16)

plt.ylabel("Values of the weights", fontsize=16)

plt.legend(loc="best", prop=dict(size=12))

plt.figure(figsize=(11, 10))

plt.title("Histogram of the weights", fontsize=18)

plt.hist(clf.coef_, bins=n_features, log=True)

plt.plot(clf.coef_[relevant_features], 5 * np.ones(len(relevant_features)),

         'ro', label="Relevant features")

plt.ylabel("features", fontsize=16)

plt.xlabel("Values of the weights", fontsize=16)

plt.legend(loc="lower left")

plt.show()

#import bokeh

#bokeh.sampledata.download() # 이 2개 라인은 최초만 실행하면 됨

from bokeh.sampledata import us_counties, unemployment

from bokeh.plotting import figure, show, output_file

from bokeh.models import HoverTool

import collections

from collections import OrderedDict

county_coordinate_xs=[

        us_counties.data[code]['lons'] for code in us_counties.data

        if us_counties.data[code]['state'] == 'ca'

        ]

county_coordinate_ys=[

        us_counties.data[code]['lats'] for code in us_counties.data

        if us_counties.data[code]['state'] == 'ca'

        ]

colors = ["#e6f2ff", "#cce5ff", "#99cbff", "#b2d8ff", "#73abe5", "#5985b2"]

county_colors = []

for county_id in us_counties.data :

    if us_counties.data[county_id]['state'] != 'ca' :

        continue

    try :

        rate = unemployment.data[county_id]

        idx = min(int(rate/2), 5)

        county_colors.append(colors[idx])

    except KeyError :

        county_colors.append("black")

output_file("california.html", title="california.py example")

TOOLS="pan, wheel_zoom, box_zoom, reset, hover, save"

p = figure(title="California Unemployment 2009",

           width=1000, height=1000, tools=TOOLS)

p.patches(county_coordinate_xs, county_coordinate_ys,

          fill_color=county_colors, fill_alpha=0.7,

          line_color="white", line_width=0.5)

mouse_hover = p.select(dict(type=HoverTool))

mouse_hover.point_policy = "follow_mouse"

mouse_hover.tooltips = collections.OrderedDict([

        ("index", "$index"), ("(x, y)", "($x, $y)"),

        ("fill color", "$color[hex, swatch]:fill_color"),])

show(p)