# Importing pandas and numpy
import pandas as pd
import numpy as np
# Reading the csv file into a pandas DataFrame
data = pd.read_csv('student_data.csv')
# Printing out the first 10 rows of our data
data[:10]
Plotting the data
First let’s make a plot of our data to see how it looks. In order to have a 2D plot, let’s ingore the rank.
# Importing matplotlib
import matplotlib.pyplot as plt
# Function to help us plot
def plot_points(data):
X = np.array(data[["gre","gpa"]])
y = np.array(data["admit"])
admitted = X[np.argwhere(y==1)]
rejected = X[np.argwhere(y==0)]
plt.scatter([s[0][0] for s in rejected], [s[0][1] for s in rejected], s = 25, color = 'red', edgecolor = 'k')
plt.scatter([s[0][0] for s in admitted], [s[0][1] for s in admitted], s = 25, color = 'cyan', edgecolor = 'k')
plt.xlabel('Test (GRE)')
plt.ylabel('Grades (GPA)')
# Plotting the points
plot_points(data)
plt.show()
For this, we’ll use the get_dummies function in pandas.
# Make dummy variables for rank
one_hot_data = pd.concat([data, pd.get_dummies(data['rank'], prefix='rank')], axis=1)
# Drop the previous rank column
one_hot_data = one_hot_data.drop('rank', axis=1)
# Print the first 10 rows of our data
one_hot_data[:10]
Scaling the data
The next step is to scale the data. We notice that the range for grades is 1.0-4.0, whereas the range for test scores is roughly 200-800, which is much larger. This means our data is skewed, and that makes it hard for a neural network to handle. Let’s fit our two features into a range of 0-1, by dividing the grades by 4.0, and the test score by 800.
# Copying our data
processed_data = one_hot_data[:]
# Scaling the columns
processed_data['gre'] = processed_data['gre']/800
processed_data['gpa'] = processed_data['gpa']/4.0
processed_data[:10]
Splitting the data into Training and Testing
In order to test our algorithm, we’ll split the data into a Training and a Testing set. The size of the testing set will be 1
sample = np.random.choice(processed_data.index, size=int(len(processed_data)*0.9), replace=False)
train_data, test_data = processed_data.iloc[sample], processed_data.drop(sample)
print("Number of training samples is", len(train_data))
print("Number of testing samples is", len(test_data))
print(train_data[:10])
print(test_data[:10])
Splitting the data into features and targets (labels)
Now, as a final step before the training, we’ll split the data into features (X) and targets (y).
Also, in Keras, we need to one-hot encode the output. We’ll do this with the to_categorical function.
import keras
# Separate data and one-hot encode the output
# Note: We're also turning the data into numpy arrays, in order to train the model in Keras
features = np.array(train_data.drop('admit', axis=1))
targets = np.array(keras.utils.to_categorical(train_data['admit'], 2))
features_test = np.array(test_data.drop('admit', axis=1))
targets_test = np.array(keras.utils.to_categorical(test_data['admit'], 2))
print(features[:10])
print(targets[:10])
Defining the model architecture
Here’s where we use Keras to build our neural network.
# Imports
import numpy as np
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.optimizers import SGD
from keras.utils import np_utils
# Building the model
model = Sequential()
model.add(Dense(128, activation='relu', input_shape=(6,)))
model.add(Dropout(.2))
model.add(Dense(64, activation='relu'))
model.add(Dropout(.1))
model.add(Dense(2, activation='softmax'))
# Compiling the model
model.compile(loss = 'categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.summary()
# Training the model
model.fit(features, targets, epochs=200, batch_size=100, verbose=0)
# Evaluating the model on the training and testing set
score = model.evaluate(features, targets)
print("\n Training Accuracy:", score[1])
score = model.evaluate(features_test, targets_test)
print("\n Testing Accuracy:", score[1])
Challenge: Play with the parameters!
You can see that we made several decisions in our training. For instance, the number of layers, the sizes of the layers, the number of epochs, etc. It’s your turn to play with parameters! Can you improve the accuracy? The following are other suggestions for these parameters. We’ll learn the definitions later in the class:
Activation function: relu and sigmoid
Loss function: categorical_crossentropy, mean_squared_error
Optimizer: rmsprop, adam, ada
Full Code:
# Importing pandas and numpy
import pandas as pd
import numpy as np
# Reading the csv file into a pandas DataFrame
data = pd.read_csv('student_data.csv')
# Printing out the first 10 rows of our data
data[:10]
# Importing matplotlib
import matplotlib.pyplot as plt
# Function to help us plot
def plot_points(data):
X = np.array(data[["gre","gpa"]])
y = np.array(data["admit"])
admitted = X[np.argwhere(y==1)]
rejected = X[np.argwhere(y==0)]
plt.scatter([s[0][0] for s in rejected], [s[0][1] for s in rejected], s = 25, color = 'red', edgecolor = 'k')
plt.scatter([s[0][0] for s in admitted], [s[0][1] for s in admitted], s = 25, color = 'cyan', edgecolor = 'k')
plt.xlabel('Test (GRE)')
plt.ylabel('Grades (GPA)')
# Plotting the points
plot_points(data)
plt.show()
# Separating the ranks
data_rank1 = data[data["rank"]==1]
data_rank2 = data[data["rank"]==2]
data_rank3 = data[data["rank"]==3]
data_rank4 = data[data["rank"]==4]
# Plotting the graphs
plot_points(data_rank1)
plt.title("Rank 1")
plt.show()
plot_points(data_rank2)
plt.title("Rank 2")
plt.show()
plot_points(data_rank3)
plt.title("Rank 3")
plt.show()
plot_points(data_rank4)
plt.title("Rank 4")
plt.show()
# Make dummy variables for rank
one_hot_data = pd.concat([data, pd.get_dummies(data['rank'], prefix='rank')], axis=1)
# Drop the previous rank column
one_hot_data = one_hot_data.drop('rank', axis=1)
# Print the first 10 rows of our data
one_hot_data[:10]
# Copying our data
processed_data = one_hot_data[:]
# Scaling the columns
processed_data['gre'] = processed_data['gre']/800
processed_data['gpa'] = processed_data['gpa']/4.0
processed_data[:10]
sample = np.random.choice(processed_data.index, size=int(len(processed_data)*0.9), replace=False)
train_data, test_data = processed_data.iloc[sample], processed_data.drop(sample)
print("Number of training samples is", len(train_data))
print("Number of testing samples is", len(test_data))
print(train_data[:10])
print(test_data[:10])
import keras
# Separate data and one-hot encode the output
# Note: We're also turning the data into numpy arrays, in order to train the model in Keras
features = np.array(train_data.drop('admit', axis=1))
targets = np.array(keras.utils.to_categorical(train_data['admit'], 2))
features_test = np.array(test_data.drop('admit', axis=1))
targets_test = np.array(keras.utils.to_categorical(test_data['admit'], 2))
print(features[:10])
print(targets[:10])
# Imports
import numpy as np
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.optimizers import SGD
from keras.utils import np_utils
# Building the model
model = Sequential()
model.add(Dense(128, activation='relu', input_shape=(6,)))
model.add(Dropout(.2))
model.add(Dense(64, activation='relu'))
model.add(Dropout(.1))
model.add(Dense(2, activation='softmax'))
# Compiling the model
model.compile(loss = 'categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.summary()
# Training the model
model.fit(features, targets, epochs=200, batch_size=100, verbose=0)
# Evaluating the model on the training and testing set
score = model.evaluate(features, targets)
print("\n Training Accuracy:", score[1])
score = model.evaluate(features_test, targets_test)
print("\n Testing Accuracy:", score[1])
댓글을 달려면 로그인해야 합니다.