In [11]:

    

# We pull in the training, validation and test sets created according to the scheme described
# in the data exploration lesson.

import pandas as pd


    

In [12]:

    

samtrain = pd.read_csv('../datasets/samsung/samtrain.csv')
samtrain['subject'].unique()


    

    
Out[12]:





array([1, 3, 5, 6])

In [13]:

    

samval = pd.read_csv('../datasets/samsung/samval.csv')
samval['subject'].unique()


    

    
Out[13]:





array([21, 22, 23, 25, 26])

In [14]:

    

samtest = pd.read_csv('../datasets/samsung/samtest.csv')
samtest['subject'].unique()


    

    
Out[14]:





array([27, 28, 29, 30])

In [15]:

    

# We use the Python RandomForest package from the scikits.learn collection of algorithms. 
# The package is called sklearn.ensemble.RandomForestClassifier

# For this we need to convert the target column ('activity') to integer values 
# because the Python RandomForest package requires that.  
# In R it would have been a "factor" type and R would have used that for classification.

# We map activity to an integer according to
# laying = 1, sitting = 2, standing = 3, walk = 4, walkup = 5, walkdown = 6
# Code is in supporting library randomforest.py

import randomforests as rf
samtrain = rf.remap_col(samtrain,'activity')
samval = rf.remap_col(samval,'activity')
samtest = rf.remap_col(samtest,'activity')


    

In [16]:

    

import sklearn.ensemble as sk
rfc = sk.RandomForestClassifier(n_estimators=500, compute_importances=True, oob_score=True)
train_data = samtrain[samtrain.columns[1:-2]]
train_truth = samtrain['activity']
model = rfc.fit(train_data, train_truth)


    

In [17]:

    

# use the OOB (out of band) score which is an estimate of accuracy of our model.
rfc.oob_score_


    

    
Out[17]:





0.97870722433460078

In [32]:

    

### TRY THIS
# use "feature importance" scores to see what the top 10 important features are
fi = enumerate(rfc.feature_importances_)
cols = samtrain.columns
[(value,cols[i]) for (i,value) in fi if value > 0.04]
## Change the value 0.04 which we picked empirically to give us 10 variables
## try running this code after changing the value up and down so you get more or less variables
## do you see how this might be useful in refining the model?
## Here is the code in case you mess up the line above
## [(value,cols[i]) for (i,value) in fi if value > 0.04]


    

    
Out[32]:





[(0.049417208797957281, 'tAccMean'),
 (0.040232503010481438, 'tAccStd'),
 (0.042021435454816999, 'tJerkMean'),
 (0.056748530984276763, 'tGyroJerkMagSD'),
 (0.058671311459878514, 'fAccMean'),
 (0.047979461996263705, 'fJerkSD'),
 (0.1378369422104955, 'angleGyroJerkGravity'),
 (0.17010923879020912, 'angleXGravity'),
 (0.044027095448683419, 'angleYGravity')]

In [19]:

    

# pandas data frame adds a spurious unknown column in 0 position hence starting at col 1
# not using subject column, activity ie target is in last columns hence -2 i.e dropping last 2 cols

val_data = samval[samval.columns[1:-2]]
val_truth = samval['activity']
val_pred = rfc.predict(val_data)

test_data = samtest[samtest.columns[1:-2]]
test_truth = samtest['activity']
test_pred = rfc.predict(test_data)


    

In [20]:

    

print("mean accuracy score for validation set = %f" %(rfc.score(val_data, val_truth)))
print("mean accuracy score for test set = %f" %(rfc.score(test_data, test_truth)))


    

    




mean accuracy score for validation set = 0.837539
mean accuracy score for test set = 0.898990

In [21]:

    

# use the confusion matrix to see how observations were misclassified as other activities
# See [5]
import sklearn.metrics as skm
test_cm = skm.confusion_matrix(test_truth,test_pred)


    

In [22]:

    

# visualize the confusion matrix


    

In [23]:

    

import pylab as pl
pl.matshow(test_cm)
pl.title('Confusion matrix for test data')
pl.colorbar()
pl.show()


    

In [24]:

    

# compute a number of other common measures of prediction goodness


    

In [33]:

    

# Accuracy
print("Accuracy = %f" %(skm.accuracy_score(test_truth,test_pred)))
# Precision
print("Precision = %f" %(skm.precision_score(test_truth,test_pred)))
# Recall
print("Recall = %f" %(skm.recall_score(test_truth,test_pred)))
# F1 Score
print("F1 score = %f" %(skm.f1_score(test_truth,test_pred)))


    

    




Accuracy = 0.898990
Precision = 0.901652
Recall = 0.898990
F1 score = 0.899470

In [29]:

    

from IPython.core.display import HTML
def css_styling():
    styles = open("../styles/custom.css", "r").read()
    return HTML(styles)
css_styling()


    

    
Out[29]:

In [29]: