from collections import defaultdict
weekRatings = defaultdict(list)
for d in datasetWithTimeValues:
day = d['timeStruct'].tm_wday
weekRatings[day].append(d['stars'])
weekAverages = {}
for d in weekRatings:
weekAverages[d]=sum(weekRatings[d]*1.0/len(weekRatings[d]))
weekAverages
x = list(weekAverages,keys())
Y=[weekAverages[x] for x in X]
import matplotlib.pylot as plt
plt.plot(X,Y)
plt.bar(X,Y)
# zoom in more to see the detail
plt.ylim(3.6, 3.8)
plt.bar(X, Y)
plt.ylim(3.6,3.8)
plt.xlabel("Weekday")
plt.ylabel("Rating")
plt.xticks([0,1,2,3,4,5,6],['S','M','T','W','T','F','S'])
plt.title("Rating as a function of weekday")
plt.bar(X,Y)
#L4 Live-coding: MatPlotLib
path = "datasets/yelp_data/review.json"
f = open(path,'r',encoding = 'utf8')
import json
import time
dataset = []
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
X1, X2 = np.meshgrid(
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
data = np.random.randint(0, 100, (10, 2))
#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()
# initialize time and x and y expenditure at initial time
t_0 = 0
init_data = np.array([3, 3.5])
# starting RK45 integration method
sys_1 = integrate.RK45(model, t_0, init_data, 1000, 0.001)
# storing initial data
sol_x = [sys_1.y[0]]
sol_y = [sys_1.y[1]]
time = [t_0]
for i in range(5000):
sys_1.step() # performing integration step
sol_x.append(
sys_1.y[0]
) # storing the results in our solution list, y is the attribute current state
sol_y.append(sys_1.y[1])
time.append(sys_1.t)
plt.figure(figsize=(20, 10))
# plotting results in a graph
plt.ylim(2, 5.5)
plt.plot(time, sol_x, 'b--', label='Country A (passive)')
plt.plot(time, sol_y, 'r--', label='Country B (passive)')
plt.ylabel('Military Expenditure (billions USD)', fontsize=16)
plt.xlabel('Time (years)', fontsize=16)
plt.legend(loc='best', fontsize=22)
plt.title('Arms Race: Passive vs. Passive', fontsize=28)
plt.show()
# !/usr/bin/python # -*- coding: UTF-8 -*- ########################## # Creator: Javy # Create Time: 20170416 # Email: [email protected] # Description: sigmoid ########################## import matplotlib.pylot as plt import numpy as np def sigmoid(z): return 1.0 / (1.0 + np.exp(-z)) z = np.arange(-7, 7, 0.1) phi_z = sigmoid(z) plt.plot(z, phi_z) plt.axvline(0.0, color='k') plt.axhspan(0.0, 1.0, facecolor='1.0', alpha=1.0, ls='dotted') plt.axhline(y=0.5, ls='dotted', color='k') plt.yticks([0.0, 0.5, 1.0]) plt.ylim(-0.1, 1.1) plt.xlable('z') plt.ylable('$\phi (z)$') plt.show()
# initialize time and x and y expenditure at initial time
t_0 = 0
init_data = np.array([5, 5])
# starting RK45 integration method
sys_1 = integrate.RK45(model, t_0, init_data, 1000, 0.001)
# storing initial data
sol_x = [sys_1.y[0]]
sol_y = [sys_1.y[1]]
time = [t_0]
for i in range(5000):
sys_1.step() # performing integration step
sol_x.append(
sys_1.y[0]
) # storing the results in our solution list, y is the attribute current state
sol_y.append(sys_1.y[1])
time.append(sys_1.t)
plt.figure(figsize=(20, 10))
# plotting results in a graph
plt.ylim(4, 10)
plt.plot(time, sol_x, 'b--', label='Country A (aggressive)')
plt.plot(time, sol_y, 'r--', label='Country B (aggressive)')
plt.ylabel('Military Expenditure (billions USD)', fontsize=16)
plt.xlabel('Time (years)', fontsize=16)
plt.legend(loc='best', fontsize=22)
plt.title('Arms Race: Aggressive vs. Aggressive', fontsize=28)
plt.show()