Created
October 13, 2017 06:26
-
-
Save dhanush/521e90097cbab964b630cb6361c354eb to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas | |
import math | |
from numpy.random import permutation | |
from sklearn import svm | |
x_cols = [] #array of all the features (column names in the file) we use to predict | |
y_cols = ['role'] #to be predicted item | |
#Create Pandas dataframe | |
training_data_frame = pandas.read_csv('train.csv') | |
#split the existing trained data to 3/4th train data and 1/4th test data | |
random_indices = permutation(training_data_frame.index) | |
test_cutoff = math.floor(len(training_data_frame)/4) | |
test_data = techDf.loc[random_indices[1:test_cutoff]] | |
train_data = techDf.loc[random_indices[test_cutoff:]] | |
## Method to predict using SVM | |
def predict_tech(predict_data): | |
clf = svm.SVC(probability=True,kernel='linear') | |
clf.fit(train_data[x_cols], train_data[y_cols].values.ravel()) | |
predictions = clf.predict(predict_data) | |
predict_probab = clf.predict_proba(predict_data) | |
return predictions,predict_probab | |
#Select one single entry to test | |
test = test_data[x_cols][0:1] | |
predictions, predict_probab = predict_tech(test) | |
#print the variables predictions and predict_probab to see the predictions & its probability |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment