import pandas as pd import numpy as np import seaborn as sns import matplotlib.pyplot as plt from pandas.plotting import scatter_matrix from sklearn.model_selection import train_test_split from sklearn.model_selection import KFold from sklearn.model_selection import cross_val_score from sklearn.metrics import classification_report from sklearn.metrics import confusion_matrix from sklearn.metrics import accuracy_score from sklearn.linear_model import LogisticRegression

df = pd.read_csv("iris.data")

df.shape

df.head(10)

df.tail()

df.describe()

scatter_matrix(df) plt.show()

array = df.values X = array[:, 0:4] y = array[:, 4]

X_train, X_validation, y_train, y_validation = train_test_split(X, y, test_size = 0.20, random_state = 7)

model = LogisticRegression() model.fit(X_train, y_train) predictions = model.predict(X_validation)

print(accuracy_score(y_validation, predictions)) print(confusion_matrix(y_validation, predictions)) print(classification_report(y_validation, predictions))

X_new = np.array([[5, 2.9, 1, 0.2]]) print(f"X_new.shape: {X_new.shape}")

new_prediction = model.predict(X_new) print(f"Prediction: {new_prediction}.")

y_predict = model.predict(X_validation) print(f"Test set predictions:\n {y_predict}") print("Test set score (np.mean): {:.2f}%".format(np.mean(y_predict == y_validation)))