Created
October 25, 2016 14:23
-
-
Save aditya1702/760cd5c95a6adf2447347e0b087bc318 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
+------------------+-----+ | |
| features|label| | |
+------------------+-----+ | |
| [1.9643, 4.5957]| 1| | |
| [2.2753, 3.8589]| 1| | |
| [2.9781, 4.5651]| 1| | |
| [2.932, 3.5519]| 1| | |
| [3.5772, 2.856]| 1| | |
| [4.015, 3.1937]| 1| | |
| [3.3814, 3.4291]| 1| | |
| [3.9113, 4.1761]| 1| | |
| [2.7822, 4.0431]| 1| | |
| [2.5518, 4.6162]| 1| | |
| [3.3698, 3.9101]| 1| | |
| [3.1048, 3.0709]| 1| | |
| [1.9182, 4.0534]| 1| | |
| [2.2638, 4.3706]| 1| | |
| [2.6555, 3.5008]| 1| | |
| [3.1855, 4.2888]| 1| | |
| [3.6579, 3.8692]| 1| | |
| [3.9113, 3.4291]| 1| | |
| [3.6002, 3.1221]| 1| | |
| [3.0357, 3.3165]| 1| | |
| [1.5841, 3.3575]| 0| | |
| [2.0103, 3.2039]| 0| | |
| [1.9527, 2.7843]| 0| | |
| [2.2753, 2.7127]| 0| | |
| [2.3099, 2.9584]| 0| | |
| [2.8283, 2.6309]| 0| | |
| [3.0473, 2.2931]| 0| | |
| [2.4827, 2.0373]| 0| | |
| [2.5057, 2.3853]| 0| | |
| [1.8721, 2.0577]| 0| | |
| [2.0103, 2.3546]| 0| | |
| [1.2269, 2.3239]| 0| | |
| [1.8951, 2.9174]| 0| | |
| [1.561, 3.0709]| 0| | |
| [1.5495, 2.6923]| 0| | |
| [1.6878, 2.4057]| 0| | |
| [1.4919, 2.0271]| 0| | |
| [0.962, 2.682]| 0| | |
| [1.1693, 2.9276]| 0| | |
| [0.8122, 2.9992]| 0| | |
| [0.9735, 3.3881]| 0| | |
| [1.25, 3.1937]| 0| | |
| [1.3191, 3.5109]| 0| | |
| [2.2292, 2.201]| 0| | |
| [2.4482, 2.6411]| 0| | |
| [2.7938, 1.9656]| 0| | |
| [2.091, 1.6177]| 0| | |
| [2.5403, 2.8867]| 0| | |
| [0.9044, 3.0198]| 0| | |
| [0.76615, 2.5899]| 0| | |
|[0.086405, 4.1045]| 1| | |
+------------------+-----+ | |
count=51 | |
----------------------------------------------------------------------- | |
from pyspark.mllib.classification import SVMWithSGD | |
data_rdd=x_df.map(lambda x:LabeledPoint(x[1],x[0])) | |
model = SVMWithSGD.train(data_rdd, iterations=1000,regParam=1.0,intercept=True,step=0.1) | |
#model.setThreshold(0.15) | |
#model.clearThreshold() | |
X=x_df.map(lambda x:x[0]).collect() | |
Y=x_df.map(lambda x:x[1]).collect() | |
------------------------------------------------------------------------- | |
pred=[] | |
for i in X: | |
pred.append(model.predict(i)) | |
print pred | |
Output: | |
[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment