Untitled

from sklearn import datasets
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn import metrics

iris = datasets.load_iris() #Loading the dataset
iris.keys()

dict_keys(['data', 'target', 'frame', 'target_names', 'DESCR', 'feature_names', 'filename', 'data_module'])
iris = pd.DataFrame(
    data= np.c_[iris['data'], iris['target']],
    columns= iris['feature_names'] + ['target']
    )
iris.head(10)
species = []

for i in range(len(iris['target'])):
    if iris['target'][i] == 0:
        species.append("setosa")
    elif iris['target'][i] == 1:
        species.append('versicolor')
    else:
        species.append('virginica')


iris['species'] = species

iris.groupby('species').size()

iris.describe()

setosa = iris[iris.species == "setosa"]
versicolor = iris[iris.species=='versicolor']
virginica = iris[iris.species=='virginica']

fig, ax = plt.subplots()
fig.set_size_inches(13, 7) # adjusting the length and width of plot

# lables and scatter points
ax.scatter(setosa['petal length (cm)'], setosa['petal width (cm)'], label="Setosa", facecolor="blue")
ax.scatter(versicolor['petal length (cm)'], versicolor['petal width (cm)'], label="Versicolor", facecolor="green")
ax.scatter(virginica['petal length (cm)'], virginica['petal width (cm)'], label="Virginica", facecolor="red")


ax.set_xlabel("petal length (cm)")
ax.set_ylabel("petal width (cm)")
ax.grid()
ax.set_title("Iris petals")
ax.legend()
# Droping the target and species since we only need the measurements
X = iris.drop(['target','species'], axis=1)

# converting into numpy array and assigning petal length and petal width
X = X.to_numpy()[:, (2,3)]
y = iris['target']

# Splitting into train and test
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.5, random_state=42)
log_reg = LogisticRegression()
log_reg.fit(X_train,y_train)
training_prediction = log_reg.predict(X_train)
training_prediction

test_prediction = log_reg.predict(X_test)
test_prediction

print("Precision, Recall, Confusion matrix, in training\n")

# Precision Recall scores
print(metrics.classification_report(y_train, training_prediction, digits=3))

# Confusion matrix
print(metrics.confusion_matrix(y_train, training_prediction))
print("Precision, Recall, Confusion matrix, in testing\n")

# Precision Recall scores
print(metrics.classification_report(y_test, test_prediction, digits=3))

# Confusion matrix
print(metrics.confusion_matrix(y_test, test_prediction))