Logistic Regression Define X and Y for Prediction

Tue Nov 12 10:38:38 EST 2019

Hi All,
I have the below code.
X = df.iloc[:, [4, 403]].values
y = df.iloc[:, 404].values

Dummy Data looks like:

host                  Mnemonic
12.234.13.6       start
22.22.44.67       something
23.44.44.14       begin

When I define the X and Y values for prediction in the train and test data, should I capture all the columns that has been "OneHotEncoded" (that is all columns with 0 and 1) for the X and Y values???

import numpy                    as np
import pandas                   as pd 
import os
import matplotlib               as mpl 
mpl.rcParams['figure.dpi'] = 400      
import matplotlib.pyplot        as plt 

# Importing the df
# Importing the df
os.chdir('c:\directory\data')                # Location of data files
df = pd.read_csv('blahblahfile.csv')

from sklearn.preprocessing import LabelEncoder
hostip = LabelEncoder()
mnemonic = LabelEncoder()
df['host_encoded'] = hostip.fit_transform(df.reported_hostname)
df['mnemonic_encoded'] = mnemonic.fit_transform(df.mnemonic)

from sklearn.preprocessing import OneHotEncoder
hostip_ohe = OneHotEncoder()
mnemonic_ohe = OneHotEncoder()
X = hostip_ohe.fit_transform(df.host_encoded.values.reshape(-1,1)).toarray()
Y = mnemonic_ohe.fit_transform(df.mnemonic_encoded.values.reshape(-1,1)).toarray()

## Add back X and Y into the original dataframe
dfOneHot = pd.DataFrame(X, columns = ["host_"+str(int(i)) for i in range(X.shape[1])])
df = pd.concat([df, dfOneHot], axis=1)

dfOneHot = pd.DataFrame(Y, columns = ["mnemonic_encoded"+str(int(i)) for i in range(Y.shape[1])])
df = pd.concat([df, dfOneHot], axis=1)

######## here is where I am not sure if all "host_" and "mnemonic_encoded" values assigned to X and Y

X = df.iloc[:, [4, 403]].values
y = df.iloc[:, 404].values

# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)

# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

# Fitting Logistic Regression to the Training set
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression(random_state = 0)
classifier.fit(X_train, y_train)

# Predicting the Test set results
y_pred = classifier.predict(X_test)

# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)

# Visualising the Training set results
from matplotlib.colors import ListedColormap
X_set, y_set = X_train, y_train
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
                     np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
             alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
                c = ListedColormap(('red', 'green'))(i), label = j)
plt.title('Logistic Regression (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()

# Visualising the Test set results
from matplotlib.colors import ListedColormap
X_set, y_set = X_test, y_test
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
                     np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
             alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
                c = ListedColormap(('red', 'green'))(i), label = j)
plt.title('Logistic Regression (Test set)')
plt.xlabel('Host IP')
plt.ylabel('Mnemonic')
plt.legend()
plt.show()