def predict_prices(dates, prices, x):
dates = np.reshape(dates, (len(dates), 1))
svr_len = SVR(kernel='linear', C=1e3)
svr_poly = SVR(kernel='poly', C=1e3, degree=2)
svr_rbf = SVR(kernel='rbf', C=1e3, gamma=0.1)
svr_lin.fit(dates, prices)
svr_poly.fit(dates, prices)
svr_rbf.fit(dates, prices)
plt.scatter(dates, prices, color='black', label='data')
plt.plot(dates, svr_rbf.predict(dates), color='red', label='RBF model')
plt.plot(dates,
svr_lin.predict(dates),
color='green',
label='Linear model')
plt.plot(dates,
svr_poly.predict(dates),
color='blue',
label='Polynomial model')
plt.xlabel('Date')
plt.ylabel('Price')
plt.title('Sipport Vector Regression')
plt.legend()
plt.show()
return svr_rbf.predict(x)[0], svr_lin.predict(x)[0], svr_poly.predict(x)[0]
def draw_scatter(heights, weights):
#创建散点图
#第一个参数为点的横坐标
#第二个参数为点的纵坐标
plt.scatter(heights, weights)
plt.xlabel('Heights')
plt.ylabel('Weights')
plt.title('Heights & Weights Of Male Students')
plt.show()
def plot_regression_line(x, y, b):
# plotting the actual points as scatter plot
plt.scatter(x, y, color="m", marker="o", s=30)
# predict response vector
y_pred = b[0] + b[1] * x
# plotting the regression line
plt.plot(x, y_pred, color="g")
# putting labels
plt.xlabel('x')
plt.ylabel('y')
# function to show plot
plt.show()
def plot_hull(self, show_points=False):
"""
Function that plots the boundaries of a convex hull using
matplotlib.pyplot. Input hull must be of type:
scipy.spatial.qhull.ConvexHull
points input must be of the original coordinates.
"""
hull = self.convex_hull(self.dots)
plt.figure()
for simplex in hull.simplices:
plt.plot(self.dots[simplex,0], \
self.dots[simplex,1], 'k-')
if show_points:
plt.scatter(self.dots[:,0], \
self.dots[:,1], s=10,c='g')
plt.scatter(self.dots[:,0], \
self.dots[:,1], s=30,c='orange')
plt.show()
def plot_hull(self, show_points=False):
"""
Function that plots the boundaries of a convex hull using
matplotlib.pyplot. Input hull must be of type:
scipy.spatial.qhull.ConvexHull
points input must be of the original coordinates.
"""
hull = self.convex_hull(self.dots)
plt.figure()
for simplex in hull.simplices:
plt.plot(self.dots[simplex,0], \
self.dots[simplex,1], 'k-')
if show_points:
plt.scatter(self.dots[:,0], \
self.dots[:,1], s=10,c='g')
plt.scatter(self.dots[:,0], \
self.dots[:,1], s=30,c='orange')
plt.show()
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
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,
DATE = datetime(now.year, now.month, now.date) # UTC date
hours = range(0, 1) # model run hour for the date
for h in hours:
FileNames = download_hrrr_nat_subsection(DATE, h)
print FileNames
# There are 50 sigma levels in HRRR
p1 = []
p2 = []
t1 = []
t2 = []
# Create a vertical temperature profile at a few points
for f in FileNames:
grbs = pygrib.open(f + '.small')
pres = grbs.select(name='Pressure')
temp = grbs.select(name='Temperature')
#
for l in range(0, 50):
p1.append(pres[l].values[1, 1] / 100)
p2.append(pres[l].values[30, 30] / 100)
t1.append(temp[l].values[1, 1] - 273.15)
t2.append(temp[l].values[30, 30] - 273.15)
#
plt.scatter(t1, p1, color='b')
plt.plot(t1, p1, color='b')
plt.scatter(t2, p2, color='r')
plt.plot(t2, p2, color='r')
plt.gca().invert_yaxis()
plt.show()
#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()
import matplotlib.pylot as plt
import pandas as pd
#fetch best performing model
best_model = RF_gscv.best_estimator_
best_model2 = MLP_gscv.best_estimator_
#fit permutation importance on test data
perm = PermutationImportance(best_model).fit(test_img, test_lab)
perm2 = PermutationImportance(best_model2).fit(test_img, test_lab)
#show weights
wghts = eli5.format_as_dataframe(eli5.explain_weights(perm))
wghts2 = eli5.format_as_dataframe(eli5.explain_weights(perm2))
#write dataframes to csv
wghts.to_csv(
'D:/studies/phd/WV3_Data_July2019/010039360030_01/L_Sabie_subset/rf_permImportance.csv',
encoding='utf-8',
index=False)
wghts2.to_csv(
'D:/studies/phd/WV3_Data_July2019/010039360030_01/L_Sabie_subset/mlp_permImportance.csv',
encoding='utf-8',
index=False)
gLawn = mlp_map_prob[:, 3]
w = x_img_arr[:, -9]
plt.scatter(w, gLawn)
plt.xlabel('proximity_to_water')
plt.ylabel('gLawn_probability')
plt.show()
plt.style.use('fivethirtyeight')
#Generate data with two classes
X, y = make_classification(class_sep=1.2, weights=[0.1, 0.9], n_informative=3,
n_redundant=1, n_features=5, n_clusters_per_class=1,
n_samples=10000, flip_y=0, random_state=10)
pca = PCA(n_components=2)
X = pca.fit_transform(X)
y = y.astype('str')
y[y=='1'] = 'L'
y[y=='0'] = 'S'
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.7, random_state=0)
X_1, X_2 = X_train[y_train=='S'], X_train[y_train=='L']
#Scatter plot of the dataset
plt.scatter(zip(*X_1)[0], zip(*X_1)[1], color='#labc9c')
plt.scatter(zip(*X_2)[0], zip(*X_2)[1], color='#e67e22')
x_coords = zip(*X_1)[0] + zip(*X_2)[0]
y_coords = zip(*X_1)[1] + zip(*X_2)[1]
plt.axis([min(x_coords), max(x_coords), min(y_coords, max(y_coords)])
plt.title("Original Dataset")
plt.show()
import pandas as pd
import numpy as np
import random as rd
import matplotlib.pylot as plt
#data
#data = pd.read_csv('data/clustering.csv')
url = 'hhttps://raw.githubusercontent.com/DUanalytics/pyAnalytics/master/data/clustering.csv'
data = pd.read_csv(url)
data.shape
data.head()
data.describe()
data.columns
#visualise
plt.scatter(data.ApplicantIncome, data.LoanAmount)
plt.xlabel('Income')
plt.ylabel('LoanAmt')
plt.show()
#standardize data : Scaling
#missing values
#https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.dropna.html
data.dtypes
data.isnull().any()
data.isnull().any(axis=1)
data.index[data.isnull().any(axis=1)]
data.iloc[6]
data.isnull().sum().sum() #75 missing values
data.isnull().sum(axis=0) #columns missing
import tensorflow as tf
import numpy as np
import matplotlib.pylot as plt
np.random.seed(5)
steps=3000
learning_rate=0.01
x_data=np.linspace(-1,1,100)[,np.newaxis]
y_data=np.squard(x_data)*0.4+np.random.randn(*x_data.shape)*0.5
x=tf.placeholder(tf.float32,[None,1])
y=tf.placeholder(tf.float32,[None,1])
weight_L1=tf.Variable(tf.random_normal([1,10]))
biases_L1=tf.Variable(tf.zeros[1,10])
Output_L1=tf.matmul(x,weight_L1)+biases_L1
L1=tf.nn.tanh(Output_L1)
weight_L2=tf.Variable(tf.random_normal([10,1]))
biases_L2=tf.Variable(tf.zeros[1,1])
Output_L2=tf.matmul(L1,weight_L2)+biases_L2
pred=tf.nn.tanh(Output_L2)
loss=tf.reduce_mean(tf.square(y-pred))
train=tf.train.GradientDescentOptimizer(learning_rate).minimize(loss)
plt.figure()
plt.scatter(x_data,y_data)
with tf.Session() as sess:
init=tf.global_variables_initializer()
sess.run(init)
for i in range(steps):
sess.run(train,feed_dict={x:x_data,y:y_data})
pred_value=sess.run(pred,feed_dict={x:x_data})
plt.plot(x_data,pred_value)
plt.show()
import pandas as pd
import matplotlib.pylot as plt
from sklearn.linear_model import LinearRegression
x = np.arange(0, 100)
y = np.arange(0, 100)
print(x)
print(y)
lr = LinearRegression()
x.ndim
y.ndim
x.shape
y.shape
x = x.reshape(-1, 1)
x.shape(-1, 1)
x.ndim
lr.fit(x, y)
plt.scatter(x, y, color='red')
plt.plot(x, lr.prdict(x), color='blue')
plt.title('Linear Regression Demo')
plt.xlabel('X')
plt.ylabel('y')
plt.show()
import numpy as np import tensorflow as tf import matplotlib.pylot as plt # 随机生成1000个点，围绕在y=0.1x+0.3的直线周围 num_points = 1000 vectors_set = [] for i in range(num_points): x1 = np.random.normal(0.0, 0.55) y1 = x1 * 0.1 + 0.3 + np.random.normal(0.0, 0.03) vectors_set.append([x1, y1]) # 生成一些样本 x_data = [v[0] for v in vectors_set] y_data = [v[1] for v in vectors_set] plt.scatter(x_data, y_data, c='r') plt.show()
