In this usecase, we build in Python the following SVM classifier (whose predictions model is shown in the 3D graph below) in order to detect if yes or no a human is present inside a room according to the room temperature, humidity and CO2 levels.
Test set observations (dots : black=occupancy and red=empty) and the model predictions (green transparent 3D shape = occupancy predictions) of the room occupancy according to temperature, CO2 and humidity levels.
We first import the needed libraries and load the dataset :
#importing libraries
import numpy as np
import pandas as pd
from matplotlib import cm
#loading the dataset
dataset = pd.read_csv('dataset.csv')
Here follows the 30 first rows over a total of 9753 in the dataset :
Dataset in Python of individual presence in a room according to levels of temperature, CO2 and humidity.
Then we split the dataset into the predictors set X (temperature, CO2 and HumidityRatio) and the independant variable y to predict (Occupancy) :
X = dataset.iloc[:,0:3].values
y = dataset.iloc[:,len(dataset.iloc[0])-1].values
We split the data into the training and the 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=0.25, random_state=0)
And we scale the values of the temperature, CO2 and humidity variables :
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)
A this step we are ready to fit the classifier to the training set data, which is done with the following code :
from sklearn.svm import SVC
classifier = SVC(kernel = 'rbf', random_state=0, gamma=100)
classifier.fit(X_train, y_train)
Once ready, we can run the classifier on the training set and the test set in order to get the predictions.
#predicting the results on the training set
y_train_pred = classifier.predict(X_train)
y_test_pred = classifier.predict(X_test)
In order to evaluate the quality of the classifier, we compute with the following code the two confusion matrix of the predictions made with the training and test set and according to them, the success ratio of the predictions :
from sklearn.metrics import confusion_matrix
cm_train = confusion_matrix(y_train, y_train_pred)
cm_test = confusion_matrix(y_test, y_test_pred)
print("Training set confusion matrix : \n"+str(cm_train))
print("Success ratio on training set : "+str(success_ratio(cm=cm_train))+"%")
print("Test set confusion matrix : \n"+str(cm_test))
print("Success ratio on test set : "+str(success_ratio(cm=cm_test))+"%")
The console shows the two following confusion matrix and success ratio for the training and test sets :
Confusion Matrix for training and test set predictions in Python
Finally, we display in a 3D graph the test set observations (dots : black=occupancy and red=empty) and the model predictions (green transparent 3D shape = occupancy predictions) of the room occupancy according to temperature, CO2 and humidity levels with the following code :
show3D(title="Test set observations (dots) and predictions (3D shape) of room occupancy according to temperature, CO2 and humidity levels.",
x_colname = 'Temperature', y_colname = 'CO2', z_colname = 'HumidityRatio', c_colname = 'Occupancy',
x_train = X_train[:,0], y_train=X_train[:,1], z_train=X_train[:,2], c_train=y_train,
x_test = X_test[:,0], y_test = X_test[:,1], z_test = X_test[:,2], c_test=y_test,
mesh_nb_pts = 50**3,
classifier = classifier
)
Here follows the 3D graph built with the test set :
Test set observations (dots : black=occupancy and red=empty) and the model predictions (green transparent 3D shape = occupancy predictions) of the room occupancy according to temperature, CO2 and humidity levels.
And we can also display a 3D graph containing the training set observations with the following function call :
show3D(title="Training set observations (dots) and predictions (3D shape) of room occupancy according to temperature, CO2 and humidity levels.",
x_colname = 'Temperature', y_colname = 'CO2', z_colname = 'HumidityRatio', c_colname = 'Occupancy',
x_train = X_train[:,0], y_train=X_train[:,1], z_train=X_train[:,2], c_train=y_train,
x_test = X_train[:,0], y_test = X_train[:,1], z_test = X_train[:,2], c_test=y_train,
mesh_nb_pts = 50**3,
classifier = classifier
)
that leads to the following 3D graph :
Training set observations (dots : black=occupancy and red=empty) and the model predictions (green transparent 3D shape = occupancy predictions) of the room occupancy according to temperature, CO2 and humidity levels.
In the both graphs, we notice that the model predictions of room occupancy (the green transparent 3D shape) fits remarquably well the occupancy observations (black dots), whereas most of the red dots (empty room observations) stay outside the green shape.
This script uses the two functions success_ratio and show3D that are defined below :
# FUNCTIONS
def success_ratio(cm):
total = cm[0][0] + cm[1][0] + cm[0][1] + cm[1][1]
return (cm[0][0] + cm[1][1]) / total
import plotly
import plotly.graph_objs as go
# displays in a 3D space the model as a 3D mesh and the test set observations as a 3D scatter plot
def show3D(title, x_colname, y_colname, z_colname, c_colname, x_train, y_train, z_train, c_train, x_test, y_test, z_test, c_test, mesh_nb_pts, classifier):
n= int( mesh_nb_pts ** (1. / 3) ) #cubic root of mesh_nb_pts
min_x = min(x_train)
min_y = min(y_train)
min_z = min(z_train)
x_size = max(x_train) - min_x
y_size = max(y_train) - min_y
z_size = max(z_train) - min_z
x_step = x_size / n
y_step = y_size / n
z_step = z_size / n
#POSITIVE (1) PREDICTIONS AS A 3D MESH
i=0
x = np.empty([n*n*n])
y = np.empty([n*n*n])
z = np.empty([n*n*n])
for xi in range(0, n):
for yi in range(0, n):
for zi in range(0, n):
x[i] = min_x + xi * x_step
y[i] = min_y + yi * y_step
z[i] = min_z + zi * z_step
i = i + 1
print("Grid of size "+str(n)+"x"+str(n)+"x"+str(n)+" generated (nb vertices = "+str(n*n*n)+").")
#computing the predictions on the grid
datagrid = pd.DataFrame( {x_colname : x, y_colname: y, z_colname : z }) #the dataframe sort the columns lexicographically
datagrid = datagrid[[x_colname, y_colname, z_colname]] #fix the correct order of columns
p = classifier.predict(datagrid);
print("Predictions on the grid computed.")
#extracting the positive (1) records from the predictions
ss = sum(p)
xx = np.empty([ss])
yy = np.empty([ss])
zz = np.empty([ss])
pp = np.empty([ss])
j = 0
for i in range(0, len(p)-1):
if(p[i] == 1):
xx[j]=x[i]
yy[j]=y[i]
zz[j]=z[i]
pp[j]=p[i]
j = j + 1
print(str(ss)+" mesh coordinates extracted with positive predictions (=1).")
#building the mesh for the predictions
trace_preds = go.Mesh3d(
x=xx,y=yy,z=zz,
alphahull=5, opacity=0.2, color='rgb(0, 256, 0)',
name = 'Predictions'
)
print("Mesh generated.")
#OBSERVATIONS 3D POINTS
#number of positive (1) and negative (0) predictions
s_pts = len(c_test)
s_pts_0 = 0
s_pts_1 = 0
for i in range(0, s_pts):
if (c_test[i] == 0) :
s_pts_0 = s_pts_0 + 1
elif (c_test[i] == 1) :
s_pts_1 = s_pts_1 + 1
else :
print("ERROR : c_test["+str(i)+"] = "+str(c_test[i]))
break
#building two set of points (x,y,z coordinates) : one for the positive (1) predictions and another one for the (0) negative predictions
x_pts_0 = np.empty([s_pts_0])
y_pts_0 = np.empty([s_pts_0])
z_pts_0 = np.empty([s_pts_0])
x_pts_1 = np.empty([s_pts_1])
y_pts_1 = np.empty([s_pts_1])
z_pts_1 = np.empty([s_pts_1])
j = 0
k = 0
for i in range(0, s_pts):
if (c_test[i] == 0) :
x_pts_0[j] = x_test[i]
y_pts_0[j] = y_test[i]
z_pts_0[j] = z_test[i]
j = j + 1
elif (c_test[i] == 1) :
x_pts_1[k] = x_test[i]
y_pts_1[k] = y_test[i]
z_pts_1[k] = z_test[i]
k = k + 1
else :
print("ERROR : c_test["+str(i)+"] = "+str(c_test[i]))
break
trace_obs_0 = go.Scatter3d(
x=x_pts_0, y=y_pts_0, z=z_pts_0,
mode='markers',
marker=dict(size=2, line=dict(color='rgb(128, 0, 0)', width=0.5), color='rgb(128, 0, 0)', opacity=1),
name='[red] Observations of class 0'
)
trace_obs_1 = go.Scatter3d(
x=x_pts_1, y=y_pts_1,z=z_pts_1,
mode='markers',
marker=dict(size=2, line=dict( color='rgba(0, 0, 0)', width=0.5 ), color='rgb(0, 0, 0)', opacity=1),
name='[black] Observations of class 1'
)
layout = go.Layout(
title=title,
scene = dict(
xaxis=dict(title=x_colname),
yaxis=dict(title=y_colname),
zaxis=dict(title=z_colname)
)
)
fig = go.Figure(data=[trace_obs_0, trace_obs_1, trace_preds], layout=layout)
plotly.offline.plot(fig)