def main():
from sklearn import datasets
iris = datasets.load_iris()
X = iris.data[: [2, 3]]
y = iris.target
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1, stratify=y)
nb = NaiveBayes()
nb.fit(X_train, y_train)
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from Perceptron import plot_decision_regions
plot_decision_regions(X, y, classifier=nb)
plt.tittle('Naive Bayes Trial')
plt.Xlabel('Sepal Length[standardized]')
plt.ylabel('Petal Length[Standardized]')
plt.show()
#plot data
plt.scatter(x1, y1, color='green')
#apply polynomial regression with degree 5
from sklearn.preprocessing import PolynomialFeatures
pol_reg = PolynomialFeatures(degree=5)
x1 = x1.reshape(-1, 1)
x_pol = pol_reg.fit_transform(x1)
#split data set for training and testing
X_train, X_test, y_train, y_test = train_test_split(x_pol,
y1,
test_size=0.2,
random_state=5)
#apply model
model = LinearRegression()
model.fit(X_train, y_train)
b1 = model.intercept_
m1 = model.coef_
print("intercept", b1)
print("slope", m1)
ac1 = model.score(X_test, y_test)
print("accuracy", ac1)
y_pred1 = model.predict(X_test)
print("prediction", y_pred1)
plt.scatter(x1, y1, color='red')
plt.plot(x1, model2.predict(pol_reg.fit_transform(x1)), color='blue')
plt.tittle("Truth or bbluff (linear regression)")
plt.xlabel("squarfit_living")
plt.ylabel("price")
plt.show()
digits = load_digits()
#Analyzing one image.
pl.gray()
pl.matshow(digits.images[0])
pl.show()
#Visualizing first 15 images with their labels.
data = list(zip(digits.images, digits.target))
plt.figure(figsize=(5, 5))
for item, (img, label) in enumerate(data[:15]):
plt.subplot(3, 5, item + 1)
plt.axis('off')
plt.imgshow(img, cmap=plt.cm.gray_r, interpolation='nearest')
plt.tittle('%i' % label)
import random
from sklean import ensemble
#Dividing our data in order to use it as a supervised learning.
n = len(digits.images)
x = digits.images.reshape((n, -1))
y = digits.target
#Random indices.
sample_index = random.sample(range(len(x)), len(x) / 5)
valid_index = [i for i in range(len(x)) if i not in sample_index]
#Images and targets to work.
sample_images = [x[i] for i in sample_index]
def normal_pdf(x: float, mu: float = 0, sigma: float = 1) -> float:
return (math.exp(-(x - mu)**2 / 2 / sigma**2) / (SQRT_TWO_PI * sigma))
import matplotlib.pyplot as plt
xs = [x / 10.0 for x in range(-50, 50)]
plt.plot(xs, [normal_pfd(x, sigma=1) for x in xs], '-', label='mu=0, sigma=1')
plt.plot(xs, [normal_pfd(x, sigma=2) for x in xs], '-', label='mu=0, sigma=2')
plt.plot(xs, [normal_pfd(x, sigma=0.5) for x in xs],
'-',
label='mu=0, sigma=0.5')
plt.plot(xs, [normal_pfd(x, mu=1) for x in xs], '-', label='mu=1, sigma=1')
plt.legend()
plt.tittle("Various Normal pdfs ")
plt.show()
def normal_cdf(x: float, mu: float = 0, sigma: float = 1) -> float:
return (1 + math.erf((x - mu) / math.sqrt(2) / sigma)) / 2
xs = [x / 10.0 for x in range(-50, 50)]
plt.plot(xs, [normal_cfd(x, sigma=1) for x in xs], '-', label='mu=0, sigma=1')
plt.plot(xs, [normal_cfd(x, sigma=2) for x in xs], '-', label='mu=0, sigma=2')
plt.plot(xs, [normal_cfd(x, sigma=0.5) for x in xs],
'-',
label='mu=0, sigma=0.5')
plt.plot(xs, [normal_cfd(x, mu=1) for x in xs], '-', label='mu=1, sigma=1')
plt.legend(loc=4) # bottom right
posicion = index
while posicion > 0 and n_lista[posicion - 1] > actual:
times += 1
n_lista[posicion] = n_lista[posicion - 1]
posicion = posicion - 1
n_lista[posicion] = actual
return n_lista
TAM = 101
eje_x = list(range(1, TAM, 1))
eje_y = []
lista_variable = []
for num in eje_x:
lista_variable = random.sample(range(0, 1000), num)
times = 0
lista_variable = insertSort_graph(lista_variable)
eje_y.append(times)
fig, ax = plt.subplots(facecolor='w', edgecolor='k')
ax.plot(eje_x, eje_y, marker="o", color="b", lineStyle='None')
ax.set_xlabel('x')
ax.set_ylabel('y')
ax.grid(True)
ax.legend(["Insertion Sort"])
plt.tittle('Insertion sort')
plt.show()
#Esta línea se ocupa para que las gráficas que se generen queden embedidas dentro de la página
%pylab inline
#importando las bibliotecas
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
#Datos de entrada
x = linscape(0,5,20) #Generando 10 puntos entre 0 y 5
fig, ax = plt.subplots(facecolor='w', edgecolor='k')
ax.plot(x, sin(x), maker="o", color="r", linestyle="None")
ax.grid(True)
ax.set_xlabel('X') #Etiqueta el eje x
ax.set_ylabel('Y') #Etiqueta el eje y
ax.grid(True)
ax.legend(["y = x**2"])
plt.tittle('Puntos')
plt.show()
fig.savefig("Gráfica.png") #Guardando la gráfica
from matplotlib import pyplot as plt
from collections import Counter
variance = [1, 2, 4, 8, 16, 32, 64, 128, 256]
bias_squared = [256, 128, 64, 32, 16, 8, 4, 2, 1]
total_error = [x + y for x, y in zip(variance, bias_squared)]
xs = [i for i, _ in enumerate(variance)]
#한 차트에 여러 개의 선을 그리기 위해 plt.plot을 여러 번 호출할 수 있다.
plt.plot(xs, variance, 'g-', label='variance') #실선
plt.plot(xs, bias_squared, 'g-', label='bias^2') #일점쇄선
plt.plot(xs, total_error, 'g-', label='total error') #점선
#각 선에 레이블을 미리 달아놔서 범례(legend)를 쉽게 그릴 수있다.
plt.legend(loc=9)
plt.xlabel("model comlexity")
plt.xticks([])
plt.tittle("The Bias-Variance Tradeoff")
plt.show()
#to avoid Dymmy trap
x=x[:,1:]
# Splitting the dataset into the Training set and Test set
from sklearn.cross_validation import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2, random_state = 0)
#multi linear regression
from sklearn.linear_model import LinearRegression
regressor=LinearRegression()
regressor.fit(x_train,y_train)
#predict
y_pred=regressor.predict(x_test)
#**x-y must be the same size so it wont plot**
#plot the result
plt.scatter(x_train,y_train,color='red')
plt.plot(x_train,regressor.predict(x_train),color='blue')
plt.tittle('multi regression model')
plt.xlabel('state-years of experience')
plt.ylabel('profit')
plt.show()
x = dataset.iloc[:, [3, 4]].values
from sklearn.cluster import KMeans
wcss = []
for i in range(1, 11):
kmeans = KMeans(n_clusters=i,
init='k-means++',
max_iter=300,
n_init=10,
random_state=0)
kmeans.fit(x)
wcss.append(kmeans.inertia_)
plt.plot(range(1, 11), wcss)
plt.tittle('The elbow method')
plt.xlabel('Number of clusters')
plt.ylabel('wcss - square of cluster distances')
plt.show
#Applying Kmens to mall data set
kmeans = KMeans(n_clusters=5,
init='k-means++',
max_iter=300,
n_init=10,
random_state=0)
y_kmeans = kmeans.fit_predict(x)
#visulize the plot
plt.scatter(x[y_kmeans == 0, 0],
from matplotlib import pyplot as plt
years = [1950, 1960, 1970, 1980, 1990, 2000, 2010]
gdp = [300.2, 543.3, 1075.9, 2862.5, 5979.6, 10289.7, 14958.3]
#x축에 연도, y축에 GDP가 있는 석ㄴ그래프를 만들자.
plt.plot(years, gdp, color='green', marker='o', linestyle='solid')
# 제목을 더하자.
plt.tittle("Nominal GDP")
# y축에 레이블을 추가하자.
plt.ylable("Billions of $")
plt.show()
x = x[:, 1:]
#split_test_train
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=.25,
random_state=0)
#multi linear regression
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(x_train, y_train)
#plot the result
plt.scatter(x_train, y_train, color='black')
plt.plot(x_train, regressor.predict(x_train), color='green')
plt.tittle('startup')
plt.xlabel('independent varaibles')
plt.ylabel('profits')
#backwards emlination
import statsmodels.api as sm
x = np.append(np.ones((50, 1)).astype(int), x, axis=1)
x_opt = x[:, [0, 1, 2, 3, 4]]
regressor_ols = sm.OLS(endog=y, exog=x_opt).fit()
regressor_ols.summary()
#dans la vidéo
y_pred=sy_y.inverse_transform(regressor.predict(sc.X.transform(np.array([6,5]))))
y_pred= sv_y.inverse_transform(regressor.predict(sc_x.transform(np.array(([6,5]))))
# Visualising the SVR results
plt.scatter(X, y, color = 'red')
plt.plot(X, regressor.predict(X), color = 'blue')
plt.title('Truth or Bluff (SVR)')
plt.xlabel('Position level')
plt.ylabel('Salary')
plt.show()
plt.scatter(X,Y, color='blue')
plt.plot (regressorr.predict(X), color='red')
plt.tittle('')
plt.xlabel('')
plt.ylabel('')
plt.show('')
# Visualising the SVR results (for higher resolution and smoother curve)
X_grid = np.arange(min(X), max(X), 0.01) # choice of 0.01 instead of 0.1 step because the data is feature scaled
X_grid = X_grid.reshape((len(X_grid), 1))
plt.scatter(X, y, color = 'red')
plt.plot(X_grid, regressor.predict(X_grid), color = 'blue')
plt.title('Truth or Bluff (SVR)')
plt.xlabel('Position level')
plt.ylabel('Salary')
plt.show()
#Fitting Linear Regression to dataset
from sklearn.linear_model import LinearRegression
lin_reg = LinearRegression()
lin_reg.fit(X, y)
#Fitting Polynomial regression to dataset
from sklearn.preprocessing import PolynomialFeatures
poly_reg = PolynomialFeatures(degree=4)
X_poly = poly_reg.fit_transform(X)
lin_reg2 = LinearRegression()
lin_reg2.fit(X_poly, y)
#Visualiizing linear regression results
plt.scatter(X, y, color='red')
plt.plot(X, lin_reg.predict(X), color='blue')
plt.tittle('Truth or Bluff (LR)')
plt.xlabel('Position level')
plt.ylabel('salary')
plt.show()
#Visualizing Polynomial regression results
X_grid = np.arange(min(X), max(X), 0.1)
X_grid = X_grid.reshape(len(X_grid), 1)
plt.scatter(X, y, color='green')
plt.plot(X_grid,
lin_reg2.predict(poly_reg.fit_transform(X_grid)),
color='yellow')
plt.tittle('Truth or Bluff (PR)')
plt.xlabel('Position level')
plt.ylabel('salary')
plt.show()
#data processing
data=pd.read_csv('Salary_Data.csv')
x=data.iloc[:,:-1].values
y=data.iloc[:,1].values
#train_split_test
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=1/3,random_state=0)
#linear regression
from sklearn.linear_model import LinearRegression
linearregression=LinearRegression()
linearregression.fit(x_train,y_train)
#predict the model
y_pred=linearregression.predict(x_test)
#plot the result
plt.scatter(x_train,y_train,color='red')
plt.plot(x_train,linearregression.predict(x_train),color='blue')
plt.tittle('linear regression')
plt.xlabel('years of experience')
plt.ylabel('salary')
plt.show()
from matplotlib import pyplot as plt
movies = ["Annie Hall", "Ben_Hue", "Casablacna", "Gandhi", "West Side Story"]
num_oscars = [5, 11, 3, 8, 10]
# 막대의 x 좌표는 [0, 1, 2, 3, 4], y좌표는 [num_oscars]로 설정
plt.bar(range(len(movies)), num_oscars)
plt.tittle("My Favorite Movies")
plt.ylabel("# of Academy Awards")
plt.xticks(range(len(movies)), movies)
plt.show()
lista_qs = lista_is.copy()
t0 = time() #Se queda el tiempo inicial
insertionSort_time(lista_is)
tiempo_is.append(round(time()-t0,6))
t0 = time ()
quickSort_time(lista_qs)
tiempo_qs.append(round(time()-t0,6))
#Imprimiendo tiempos parciales de ejecución
print("Tiempos parciales de ejcución en INSERT SORT {} [s]\n".format(tiempo_is))
print("Tiempos parciales de ejcución en QUICK SORT {} [s]".format(tiempo_qs))
#Imprimiendo tiempos totales de ejecución
#Para calcular el tiempo total se aplica la función sum() a las listas de tiempo
print("Tiempo total de ejcución en INSERT SORT {} [s]\n".format(sum(tiempo_is)))
print("Tiempo total de ejcución en QUICK SORT {} [s]\n".format(sum(tiempo_qs)))
#Generandola gráfica
fig, ax = subplots()
ax.plot(datos, tiempo_is, label ="insert sort", marker="*", color="r")
ax.plot(datos, tiempo_qs, label ="quick sort", marker="o", color="b")
ax.set_xlabel('Datos')
ax.set_ylabel('Tiempo')
ax.grid(True)
ax.legend(loc=2);
plt.tittle('Tiempo de ejcución [s] (insert vs. quick)')
plt.show()
new_data.plot.scatter(x='like' , y='Total Interaciones')
# In[286]:
dataset.plot.box()
# In[ ]:
for c in dataset.columns.sort_values();
plt.figure()
dataset[c].hist()
plt.tittle(t)
# In[299]:
grouped = dataset.groupby("Dia_Semana").mean()
grouped["Total Interaciones"].plot()
plt.show()
# In[331]:
dataset_col = dataset.Dia_Semana.value_counts()
dataset_col.plot.bar()
from matplotlib import pyplot as plt
from collections import Counter
friends = [70, 65, 72, 63, 71, 64, 60, 64, 67]
minutes = [175, 170, 205, 120, 220, 130, 105, 145, 190]
lables = ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i']
plt.scatter(friends, minutes)
#각 포인트에 레이블을 달자,.
for label, friend_count, minute_count in zip(lables, friends, minutes):
plt.annotate(
label,
xy=(friend_count, minute_count), #레이블을 데이터 포인트 근처에 두되
xytext=(5, -5), # 약간 떨어져 있게 하자.
textcoords='offset points')
plt.tittle("Daily Minutes vs. Number of Friens")
plt.xlabel("# of friends")
plt.ylabel("daily minutes spent on the site")
plt.show()
plt.legend()
plt.show()
#pie chart
from matplotlib import pyplot as plt
lab = 'python', 'c++', 'ruby', 'java'
sizes = 215, 130, 245, 210
cols = ('c', 'm', 'r', 'b')
plt.pie(sizes,
labels=lab,
explode=(0, 0, 0.2, 0),
colors=cols,
startangle=140,
autopct='%0.2f%%',
shadow=False)
plt.tittle('pie')
plt.show()
help(plt.pie)
#scatter
from matplotlib import pyplot as plt
x = [1, 2, 3, 1, 5, 5, 1, 8, 2, 3, 3, 3, 6]
y = [7, 7, 5, 6, 1, 5, 2, 5, 3, 6, 4, 6, 6]
x1 = [4, 5, 4, 5, 8, 6, 4, 8, 2, 5, 0]
y1 = [6, 8, 9, 9, 8, 6, 5.2, 3.2, 5, 6, 0]
plt.scatter(x, y, label='high', color='r')
plt.scatter(x1, y1, label='low', color='g')
plt.title('scatter Chart') #label-axis name
plt.xlabel('Xaxis')
plt.ylabel('Yaxis')
plt.legend() #display label axis name in chart
import matplotlib.pyplot as plt
import numpy as np
fs=input('Enter value for fs:')
f=input('Enter value for f:')
x=np.arange(0,100,1)
y1=np.sin(2*np.pi*f*x/fs)
y2=np.cos(2*np.pi*f*x/fs)
y=y1+y2
plt.subplot(1,3,1)
plt.plot(x,y1)
plt.tittle('sin wave')
plt.xlabel('------------->t')
plt.y1label('------------>voltage')
plt.subplot(1,3,2)
plt.plot(x,y2)
plt.tittle('cos wave')
plt.xlabel('------------->t')
plt.y2label('------------>voltage')
plt.subplot(1,3,3)
plt.plot(x,y)
plt.tittle('sin wave and cos wave')
plt.xlabel('------------->t')
plt.ylabel('------------>voltage')
plt.show()
eating = [1, 2, 1, 3, 2]
playing = [3, 4, 2, 6, 1]
working = [4, 5, 8, 3, 9]
plt.plot([], [], color='m', label='sleeping', linewidth=5)
plt.plot([], [], color='c', label='eating', linewidth=5)
plt.plot([], [], color='r', label='working', linewidth=5)
plt.plot([], [], color='k', label='playing', linewidth=5)
plt.stackplot(days,
sleeping,
eating,
working,
playing,
colors=['m', 'c', 'r', 'k'])
plt.tittle('stackplot')
plt.xlabel('day')
plt.ylabel('Activities')
plt.legend() # to setting up labels
plt.grid(True, color='k') # back group grid with black color
plt.show() # generate graph
# Pie plots
from matplotlib import pyplot as plt
slices = [7, 2, 2, 13] # percentage of the Pie.
labs = ['IBM', 'TCS', 'WIPRO', 'INFY']
col = ['m', 'c', 'r', 'g']
plt.pie(slices,
labels=labs,
colors=col,