Python入门项目

最近学习Python在网上找到一个很好的小入门级的项目但是发现由于版本的问题，不能直接运行，于是自己修改了一下

原文链接：https://segmentfault.com/a/1190000017067753

代码实现：

 

import sys

from pandas.plotting import scatter_matrix

print('Python: {}'.format(sys.version))
# scipy
import scipy

print('scipy: {}'.format(scipy.__version__))
# numpy
import numpy

print('numpy: {}'.format(numpy.__version__))
# matplotlib
import matplotlib
import matplotlib.pyplot as plt

print('matplotlib: {}'.format(matplotlib.__version__))
# pandas
import pandas

print('pandas: {}'.format(pandas.__version__))
# scikit-learn
import sklearn
from sklearn.model_selection import KFold
from sklearn.linear_model import LogisticRegression
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

print('sklearn: {}'.format(sklearn.__version__))

# Load dataset
url = "https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data"
names = ['sepal-length', 'sepal-width', 'petal-length', 'petal-width', 'class']
dataset = pandas.read_csv(url, names=names)

# shape
print(dataset.shape)

# descriptions
print(dataset.describe())

# box and whisker plots
dataset.plot(kind='box', subplots=True, layout=(2, 2), sharex=False, sharey=False)
plt.show()

# histograms
dataset.hist()
plt.show()

# scatter plot matrix
scatter_matrix(dataset)
plt.show()

# Split-out validation dataset
array = dataset.values
X = array[:, 0:4]
Y = array[:, 4]
validation_size = 0.20
seed = 7
X_train, X_validation, Y_train, Y_validation = sklearn.model_selection.train_test_split(X, Y, test_size=validation_size, random_state=seed)

# Test options and evaluation metric
seed = 7
scoring = 'accuracy'

#Spot Check Algorithms
models = []
models.append(('LR', LogisticRegression()))
models.append(('LDA', LinearDiscriminantAnalysis()))
models.append(('KNN', sklearn.neighbors.KNeighborsClassifier()))
models.append(('CART', sklearn.tree.DecisionTreeClassifier()))
models.append(('NB', sklearn.naive_bayes.GaussianNB()))
models.append(('SVM', sklearn.svm.SVC()))
# evaluate each model in turn
results = []
names = []
for name, model in models:
    kfold = KFold(n_splits=10, random_state=seed)
    cv_results = sklearn.model_selection.cross_val_score(model, X_train, Y_train, cv=kfold, scoring=scoring)
    results.append(cv_results)
    names.append(name)
    msg = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
    print(msg)

# Compare Algorithms
fig = plt.figure()
fig.suptitle('Algorithm Comparison')
ax = fig.add_subplot(111)
plt.boxplot(results)
ax.set_xticklabels(names)
plt.show()

# Make predictions on validation dataset
knn = sklearn.neighbors.KNeighborsClassifier()
knn.fit(X_train, Y_train)
predictions = knn.predict(X_validation)
print(sklearn.metrics.accuracy_score(Y_validation, predictions))
print(sklearn.metrics.confusion_matrix(Y_validation, predictions))
print(sklearn.metrics.classification_report(Y_validation, predictions))