Is there a way for me to view the classes of particular instances in binary classified dataset using scikit learn
Is there a way for me to view the classes of particular instances in a binary classified dataset(classes are 0 or 1) using the scikit learn library. I have a program that performs knn on a dataset and inserts the model built into a database. I want to view instances in the the data that are classified as 0 or 1. This is the link to the dataset I am using https://drive.google.com/open?id=0B9cQtdthFqv3YVNBNk1peVltZkk from sklearn import neighbors,datasets,preprocessing from sklearn.cross_validation import train_test_split import urllib.request from sklearn.metrics import accuracy_score import pandas as pd import matplotlib.pyplot as plt from sklearn import model_selection from sklearn.metrics import precision_recall_fscore_support as score from sklearn.externals import joblib from sklearn.model_selection import cross_val_score from pandas import read_csv from sklearn.ensemble import ExtraTreesClassifier import pandas as pd import numpy as np import sys import pickle import mysql.connector as mc def doSupervised(username,fileid,filename): try: connection = mc.connect (host = "localhost", user = "**", passwd = "**", db = "**") except mc.Error as e: print("Error %d: %s" % (e.args, e.args)) sys.exit(1) cursor = connection.cursor() # load data dataframe = pd.DataFrame.from_csv(filename) X= np.array(dataframe) y = np.array(dataframe['Class']) # fit an Extra Trees model to the data model = ExtraTreesClassifier() model.fit_transform(X, y) # display the relative importance of each attribute #print(model.feature_importances_) X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2) clf = neighbors.KNeighborsClassifier(algorithm='auto') #fit the data to the model clf.fit(X_train, y_train) y_pred = clf.predict(X_test) #print (y_pred) algorithmType="Supervised" accuracy =accuracy_score(y_test, y_pred ) print(accuracy) #save classifier to a file name="supervisedmodel.pkl" data = joblib.dump(clf, name) #name = 'supervisedmodel.sav' #data = pickle.dump(clf, open(name, 'wb')) sql_command = "INSERT INTO machinelearningmodel (username, fileID, name,data,accuracy,algorithmType ) VALUES (%s, %s, %s, %s, %s, %s)", (username, str(fileid), name, str(data), str(accuracy),algorithmType) cursor.execute(*sql_command) #print(sql_command) cursor.close() connection.commit() connection.close() if __name__ == "__main__": doSupervised(sys.argv,sys.argv,sys.argv)
Final output don't return correct result in my Python multiprocessing code
how to fix the “W293 blank line contains whitespace”
How to create LinkExtractor rule which based on href in Scrapy
Accessing an Enum in Python
list comprehension returns error while try / except doesn't
Coding a recursive function on Python 3.0
How do I use the result of a function in a string?
How to stop Celery creating duplicated users in this task?
I'm trying to run an if-then true-false statement. How, I continuously receive errors when attempting to do so
Creating vertical dictionary from text file
Unable to import module even after adding __init__.py
Bluehost-Premature end of headers in python script
numpy.array_split() odd behavior
Memory allocation for numpy.array with copy=False?
Draw contours of detected objects using python and opencv
simple web crawler i need to eliminate the duplicate URL that present in the array