def visual_inspection(raw_signal_list,
filtered_signal_list,
begin_sec, end_sec):
import matplotlib.pylot as plt
for raw_signal, filtered_signal in zip(raw_signal_list,
filtered_signal_list):
plt.figure(figsize=(20, 20))
plt.plot(raw_signal.T)
plt.plot(filterd_signal.T)
plt.xlim(begin_sec * 1000, end_sec * 1000)
plt.legend(['raw', 'filtered'])
plt.show()
from matplotlib.colors import ListedColormap
X_set, y_set = X_train, y_train
X1, X2 = np.meshgrid(
np.arange(start=X_set[:, 0].min() - 1,
stop=X_set[:, 0].max() + 1,
step=0.01),
np.arange(start=X_set[:, 1].min() - 1,
stop=X_set[:, 1].max() + 1,
step=0.01))
plt.contourf(X1,
X2,
classifer.predict(np.array([X1.ravel(),
X2.ravel()]).T).reshape(X1.shape),
alpha=0.75,
cmap=ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
plt.scatter(X_set[y_set == j, 0],
X_set[y_set == j, 1],
c=ListedColormap(('red', 'green'))(i),
label=j)
plt.title('Classifier (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()
# Visualising the Test set results
from matplotlib.colors import ListedColormap
X_set, y_set = X_test, y_test
stdout.flush()
stdout.write("\n")
# Calculate and print the position of minimum in MSE
msemin = np.argmin(mse)
print("Suggested number of components: ", msemin+1)
stdout.write("\n")
if plot_components is True:
with plt.style.context(('ggplot')):
plt.plot(component, np.array(mse), '-v', color = 'blue', mfc='blue')
plt.plot(component[msemin], np.array(mse)[msemin], 'P', ms=10, mfc='red')
plt.xlabel('Number of PLS components')
plt.ylabel('MSE')
plt.title('PLS')
plt.xlim(xmin=-1)
plt.show()
# Run PLS with suggested number of components
pls = PLSRegression(n_components=msemin+1)
pls.fit(X_calib, Y_calib)
Y_pred = pls.predict(X_valid)
# Calculate and print scores
score_p = r2_score(Y_valid, Y_pred)
mse_p = mean_squared_error(Y_valid, Y_pred)
sep = np.std(Y_pred[:,0]-Y_valid)
rpd = np.std(Y_valid)/sep
bias = np.mean(Y_pred[:,0]-Y_valid)
print('R2: %5.3f' % score_p)
my_salary = df['salary'] > 60000
df[df['salary'] > 60000] or df[my_salary]
df.as_matrix() #returns numpy array.
#Data Visualization Reference.
import numpy as np
import pandas as pd
import matplotlib.pylot as plt
%matplotlib inline #jupyter notebook only. below line for everything else.
plt.show()
x = np.arange(0, 10)
y = x ** 2
plt.plot(x, y, 'red') #shows red line.
plt.plot(x, y, '*') #shows stars on graph.
plt.plot(x, y, 'r--') #shows red line with dashes.
plt.xlim(0, 4) #shows x-axis limits at 0 and 4.
plt.ylim(0, 10) #shows y-axis limits at 0 and 10.
plt.title("title goes here")
plt.xlabel('x label goes here')
plt.ylabel('y label goes here')
mat = np.arange(0, 100).reshape(10, 10) #makes array.
plt.imshow(mat, cmap = 'RdYlGn')
mat = np.random.randint(0, 1000, (10, 10))
plt.imshow(mat)
plt.colorbar()
df = pd.read_csv('salaries.csv')
df.plot(x = 'salary', y = 'age', kind = 'scatter') #kind could be 'line' or whatever else you need.
#SciKit-Learn Reference/Pre-Processing.
import numpy as np
from sklearn.preprocessing import MinMaxScaler
#Rafael Almeida
# K-MEANS
import pandas as pd
import numpy as np
import matplotlib.pylot as plt
%matplotlib inline
df = pd.DataFrame({
'x': [12, 20, 28, 18, 29, 33, 24, 45, 45, 52, 51, 52, 55, 53, 55, 61, 64, 69, 72],
'y': [39, 36, 30, 52, 54, 46, 55, 59, 63, 70, 66, 63, 58, 23, 14, 8, 19, 7, 24]
})
np.random.seed(200)
k = 3
# centroids[i] = [x,y]
centroids = {
i +1 [np.random.randint(0, 80), np.random.randint(0, 80)]
for i in range (k)
}
fig = plt.figure(figsize = (5,5))
plt.scatter(df['x'], df['y'], color= 'k')
colmap = {1: 'r', 2: 'g', 3: 'b'}
for i in centroids.keys():
plt.scatter(*centroids[i], color=colmap[i])
plt.xlim(0, 80)
plt.ylim(0, 80)
plt.show()