Machine Learing Project: iris

Machine Learing project on iris dataset

Importing Library

# import warnings filter
from warnings import simplefilter
# ignore all future warnings
simplefilter(action='ignore', category=FutureWarning)


import numpy as np
import pandas as pd
import seaborn as sns
sns.set_palette('husl')
import matplotlib.pyplot as plt
%matplotlib inline

from sklearn import metrics
from sklearn.neighbors import KNeighborsClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split

Reading .csv file

data = pd.read_csv('Iris.csv')

Preview of Data

data.head()

data.info()

data.describe()

data['Species'].value_counts()

Data Visualization

tmp = data.drop('Id', axis=1)
g = sns.pairplot(tmp, hue='Species', markers='+')
plt.show()

g = sns.violinplot(y='Species', x='SepalLengthCm', data=data, inner='quartile')
plt.show()
g = sns.violinplot(y='Species', x='SepalWidthCm', data=data, inner='quartile')
plt.show()
g = sns.violinplot(y='Species', x='PetalLengthCm', data=data, inner='quartile')
plt.show()
g = sns.violinplot(y='Species', x='PetalWidthCm', data=data, inner='quartile')
plt.show()

Modeling with scikit-learn

X = data.drop(['Id', 'Species'], axis=1)
y = data['Species']
# print(X.head())
print(X.shape)
# print(y.head())
print(y.shape)

y_prediction = model.predict(x_test)

Train and test on the same dataset

# experimenting with different n values
k_range = list(range(1,26))
scores = []
for k in k_range:
    knn = KNeighborsClassifier(n_neighbors=k)
    knn.fit(X, y)
    y_pred = knn.predict(X)
    scores.append(metrics.accuracy_score(y, y_pred))

plt.plot(k_range, scores)
plt.xlabel('Value of k for KNN')
plt.ylabel('Accuracy Score')
plt.title('Accuracy Scores for Values of k of k-Nearest-Neighbors')
plt.show()

logreg = LogisticRegression()
logreg.fit(X, y)
y_pred = logreg.predict(X)
print(metrics.accuracy_score(y, y_pred))
### mean_squared_error

Split the dataset into a training set and a testing set

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=5)
print(X_train.shape)
print(y_train.shape)
print(X_test.shape)
print(y_test.shape)

# experimenting with different n values
k_range = list(range(1,26))
scores = []
for k in k_range:
    knn = KNeighborsClassifier(n_neighbors=k)
    knn.fit(X_train, y_train)
    y_pred = knn.predict(X_test)
    scores.append(metrics.accuracy_score(y_test, y_pred))

plt.plot(k_range, scores)
plt.xlabel('Value of k for KNN')
plt.ylabel('Accuracy Score')
plt.title('Accuracy Scores for Values of k of k-Nearest-Neighbors')
plt.show()

accuracy_score

logreg = LogisticRegression()
logreg.fit(X_train, y_train)
y_pred = logreg.predict(X_test)
print(metrics.accuracy_score(y_test, y_pred))

Choosing KNN to Model Iris Species Prediction with k = 12

knn = KNeighborsClassifier(n_neighbors=12)
knn.fit(X, y)

# make a prediction for an example of an out-of-sample observation
knn.predict([[6, 3, 4, 2]])