shubham0204

fun classifyText( text : String ) : Int {
    val class_1_probability = findProbabilityGivenSample( text , positiveBagOfWords )
    val class_2_probability = findProbabilityGivenSample( text , negativeBagOfWords )
    if ( class_1_probability > class_2_probability ) {
        return CLASS_POSITIVE
    }
    else if ( class_1_probability < class_2_probability ) {
        return CLASS_NEGATIVE
    }
}

shubham0204

class Classifier( private var positiveBagOfWords : Array<String> , private var negativeBagOfWords : Array<String>) {

    companion object {

        val CLASS_POSITIVE = 0
        val CLASS_NEGATIVE = 1

        private val englishStopWords = arrayOf(
            "i", "me", "my", "myself", "we", "our", "ours", "ourselves", "you", "your", "yours", "yourself", "yourselves",
            "he", "him", "his", "himself", "she", "her", "hers", "herself", "it", "its", "itself", "they", "them", "their",

shubham0204

shubham0204

import pandas as pd
import numpy as np
import tensorflow as tf
from sklearn.model_selection import train_test_split

data = pd.read_csv( 'graduate_admission_prediction/Admission_Predict_Ver1.1.csv' )
data.head()

continuous_features = data[ ['GRE Score','TOEFL Score','University Rating','SOP','LOR ','CGPA'] ].values / 100 
categorical_research_features = data[ [ 'Research' ] ].values 

shubham0204

def mean_squared_error( Y , y_pred ):
    return tf.reduce_mean( tf.square( y_pred - Y ) )

def mean_squared_error_deriv( Y , y_pred ):
    return tf.reshape( tf.reduce_mean( 2 * ( y_pred - Y ) ) , [ 1 , 1 ] )
    
def h ( X , weights , bias ):
    return tf.tensordot( X , weights , axes=1 ) + bias

shubham0204

num_epochs = 10
num_samples = X.shape[0]
batch_size = 10
learning_rate = 0.001

dataset = tf.data.Dataset.from_tensor_slices(( X , Y )) 
dataset = dataset.shuffle( 500 ).repeat( num_epochs ).batch( batch_size )
iterator = dataset.__iter__()

shubham0204

num_features = X.shape[1]
weights = tf.random.normal( ( num_features , 1 ) ) 
bias = 0

epochs_plot = list()
loss_plot = list()

for i in range( num_epochs ) :
    
    epoch_loss = list()

shubham0204

output = h( test_X , weights , bias ) 
labels = test_Y

accuracy_op = tf.metrics.MeanAbsoluteError() 
accuracy_op.update_state( labels , output )
print( 'Mean Absolute Error = {}'.format( accuracy_op.result().numpy() ) )

shubham0204

private var weights : DoubleArray
private var bias = 0.0

// numFeatures is a value of type Int and refers to the number of features.
// It is the length of the X vector.

init {
    val random = Random()
    val weights = DoubleArray(numFeatures) 
    for (x in 0 until numFeatures) {

shubham0204

private fun batch ( x : Array<DoubleArray> , y : DoubleArray , batchSize : Int ) : List<List<Pair<DoubleArray,Double>>> {
    val data = x.zip( y.toTypedArray() )
    return data.chunked( batchSize )
}

private fun forwardPropogate( x : DoubleArray ) : Double {
    return MathOps.dot( this.weights , x ) + bias
}