探索监督式机器学习算法

import matplotlib.pyplot as plt
from pandas import read_csv
import os

# Load data
data_path = os.path.join(os.getcwd(), "data/blood-pressure.txt")
dataset = read_csv(data_path, delim_whitespace=True)

# We have 30 entries in our dataset and four features. The first feature is the ID of the entry.
# The second feature is always 1. The third feature is the age and the last feature is the blood pressure.
# We will now drop the ID and One feature for now, as this is not important.
dataset = dataset.drop(['ID', 'One'], axis=1)

# And we will display this graph
%matplotlib inline
dataset.plot.scatter(x='Age', y='Pressure')

# Now, we will assume that we already know the hypothesis and it looks like a straight line
h = lambda x: 84 + 1.24 * x

# Let's add this line on the chart now
ages = range(18, 85)
estimated = []

for i in ages:
    estimated.append(h(i))

plt.plot(ages, estimated, 'b')

import numpy as np
# Let's calculate the cost for the hypothesis above

h = lambda x, theta_0, theta_1: theta_0 + theta_1 * x

def cost(X, y, t0, t1):
    m = len(X) # the number of the training samples
    c = np.power(np.subtract(h(X, t0, t1), y), 2)
    return (1 / (2 * m)) * sum(c)

X = dataset.values[:, 0]
y = dataset.values[:, 1]
print('J(Theta) = %2.2f' % cost(X, y, 84, 1.24))

import matplotlib.pyplot as plt

fig = plt.figure()

# Generate the data
theta_1 = np.arange(-10, 14, 0.1)

J_cost = []
for t1 in theta_1:
    J_cost += [ cost(X, y, 0, t1) ]

plt.plot(theta_1, J_cost)

plt.xlabel(r'$\theta_1$')
plt.ylabel(r'$J(\theta)$')

plt.show()

import math
# Example of the simple gradient descent algorithm taken from Wikipedia

cur_x = 2.5 # The algorithm starts at point x
gamma = 0.005 # Step size multiplier
precision = 0.00001
previous_step_size = cur_x

df = lambda x: 2 * x * math.cos(x)

# Remember the learning curve and plot it 

while previous_step_size > precision:
    prev_x = cur_x
    cur_x += -gamma * df(prev_x)
    previous_step_size = abs(cur_x - prev_x)

print("The local minimum occurs at %f" % cur_x)

from sklearn.linear_model import LinearRegression
# LinearRegression uses the gradient descent method

# Our data
X = dataset[['Age']]
y = dataset[['Pressure']]

regr = LinearRegression()
regr.fit(X, y)

# Plot outputs
plt.xlabel('Age')
plt.ylabel('Blood pressure')

plt.scatter(X, y,  color='black')
plt.plot(X, regr.predict(X), color='blue')

plt.show()
plt.gcf().clear()

<matplotlib.figure.Figure at 0x120fae1d0>

print( 'Predicted blood pressure at 25 y.o.   = ', regr.predict(25) )
print( 'Predicted blood pressure at 45 y.o.   = ', regr.predict(45) )
print( 'Predicted blood pressure at 27 y.o.   = ', regr.predict(27) )
print( 'Predicted blood pressure at 34.5 y.o. = ', regr.predict(34.5) )
print( 'Predicted blood pressure at 78 y.o.   = ', regr.predict(78) )

Predicted blood pressure at 25 y.o.   =  [[ 122.98647692]]
Predicted blood pressure at 45 y.o.   =  [[ 142.40388395]]
Predicted blood pressure at 27 y.o.   =  [[ 124.92821763]]
Predicted blood pressure at 34.5 y.o. =  [[ 132.20974526]]
Predicted blood pressure at 78 y.o.   =  [[ 174.44260555]]

from sklearn.linear_model import LogisticRegression

# Data
data_path = os.path.join(os.getcwd(), "data/shuttle-landing-control.csv")
dataset = read_csv(data_path, header=None, 
                    names=['Auto', 'Stability', 'Error', 'Sign', 'Wind', 'Magnitude', 'Visibility'],
                    na_values='*').fillna(0)

# Prepare features
X = dataset[['Stability', 'Error', 'Sign', 'Wind', 'Magnitude', 'Visibility']]
y = dataset[['Auto']].values.reshape(1, -1)[0]

model = LogisticRegression()
model.fit(X, y)

# For now, we're missing one important concept. We don't know how well our model 
# works, and because of that, we cannot really improve the performance of our hypothesis. 
# There are a lot of useful metrics, but for now, we will validate how well 
# our algorithm performs on the dataset it learned from.
"Score of our model is %2.2f%%" % (model.score(X, y) * 100)

from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import cross_val_score

# Ground truth function
ground_truth = lambda X: np.cos(15 + np.pi * X)

# Generate random observations around the ground truth function
n_samples = 15
degrees = [1, 4, 30] 

X = np.linspace(-1, 1, n_samples)
y = ground_truth(X) + np.random.randn(n_samples) * 0.1

plt.figure(figsize=(14, 5))

models = {}

# Plot all machine learning algorithm models
for idx, degree in enumerate(degrees):
    ax = plt.subplot(1, len(degrees), idx + 1)
    plt.setp(ax, xticks=(), yticks=())
    
    # Define the model
    polynomial_features = PolynomialFeatures(degree=degree)
    model = make_pipeline(polynomial_features, LinearRegression())
    
    models[degree] = model
    
    # Train the model
    model.fit(X[:, np.newaxis], y)
    
    # Evaluate the model using cross-validation
    scores = cross_val_score(model, X[:, np.newaxis], y)
    
    X_test = X
    plt.plot(X_test, model.predict(X_test[:, np.newaxis]), label="Model")
    plt.scatter(X, y, edgecolor='b', s=20, label="Observations")
    
    plt.xlabel("x")
    plt.ylabel("y")
    plt.ylim((-2, 2))
    
    plt.title("Degree {}\nMSE = {:.2e}".format(
        degree, -scores.mean()))

plt.show()

from sklearn.model_selection import learning_curve, ShuffleSplit

# Plot learning curves
plt.figure(figsize=(20, 5))

for idx, degree in enumerate(models):
    ax = plt.subplot(1, len(degrees), idx + 1)
    
    plt.title("Degree {}".format(degree))
    plt.grid()
    
    plt.xlabel("Training examples")
    plt.ylabel("Score")
    
    train_sizes = np.linspace(.6, 1.0, 6)
    
    # Cross-validation with 100 iterations to get a smoother mean test and training
    # score curves, each time with 20% of the data randomly selected as a validation set.
    cv = ShuffleSplit(n_splits=100, test_size=0.2, random_state=0)
    
    model = models[degree]
    train_sizes, train_scores, test_scores = learning_curve(
        model, X[:, np.newaxis], y, cv=cv, train_sizes=train_sizes, n_jobs=4)
    
    train_scores_mean = np.mean(train_scores, axis=1)
    test_scores_mean = np.mean(test_scores, axis=1)
    
    plt.plot(train_sizes, train_scores_mean, 'o-', color="r",
             label="Training score")
    plt.plot(train_sizes, test_scores_mean, 'o-', color="g",
             label="Test score")
    
    plt.legend(loc = "best")

plt.show()

import os
from pandas import read_csv, concat

# Load data
data_path = os.path.join(os.getcwd(), "data/titanic.csv")
dataset = read_csv(data_path, skipinitialspace=True)

dataset.head(5)

import pandas as pd

# We need to drop some insignificant features and map the others.
# Ticket number and fare should not contribute much to the performance of our models.
# Name feature has titles (e.g., Mr., Miss, Doctor) included.
# Gender is definitely important.
# Port of embarkation may contribute some value.
# Using port of embarkation may sound counter-intuitive; however, there may 
# be a higher survival rate for passengers who boarded in the same port.

dataset['Title'] = dataset.Name.str.extract(' ([A-Za-z]+)\.', expand=False)
dataset = dataset.drop(['PassengerId', 'Ticket', 'Cabin', 'Name'], axis=1)

pd.crosstab(dataset['Title'], dataset['Sex'])

# We will replace many titles with a more common name, English equivalent,
# or reclassification
dataset['Title'] = dataset['Title'].replace(['Lady', 'Countess','Capt', 'Col',\
 	'Don', 'Dr', 'Major', 'Rev', 'Sir', 'Jonkheer', 'Dona'], 'Other')

dataset['Title'] = dataset['Title'].replace('Mlle', 'Miss')
dataset['Title'] = dataset['Title'].replace('Ms', 'Miss')
dataset['Title'] = dataset['Title'].replace('Mme', 'Mrs')
    
dataset[['Title', 'Survived']].groupby(['Title'], as_index=False).mean()

# Now we will map alphanumerical categories to numbers
title_mapping = { 'Mr': 1, 'Miss': 2, 'Mrs': 3, 'Master': 4, 'Other': 5 }
gender_mapping = { 'female': 1, 'male': 0 }
port_mapping = { 'S': 0, 'C': 1, 'Q': 2 }

# Map title
dataset['Title'] = dataset['Title'].map(title_mapping).astype(int)

# Map gender
dataset['Sex'] = dataset['Sex'].map(gender_mapping).astype(int)

# Map port
freq_port = dataset.Embarked.dropna().mode()[0]
dataset['Embarked'] = dataset['Embarked'].fillna(freq_port)
dataset['Embarked'] = dataset['Embarked'].map(port_mapping).astype(int)

# Fix missing age values
dataset['Age'] = dataset['Age'].fillna(dataset['Age'].dropna().median())

dataset.head()

from sklearn.model_selection import KFold, train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import PolynomialFeatures, StandardScaler

from sklearn.neural_network import MLPClassifier
from sklearn.svm import SVC

# Prepare the data
X = dataset.drop(['Survived'], axis = 1).values
y = dataset[['Survived']].values

X = StandardScaler().fit_transform(X)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state = None)

# Prepare cross-validation (cv)
cv = KFold(n_splits = 5, random_state = None)

# Performance
p_score = lambda model, score: print('Performance of the %s model is %0.2f%%' % (model, score * 100))

# Classifiers
names = [
    "Logistic Regression", "Logistic Regression with Polynomial Hypotheses",
    "Linear SVM", "RBF SVM", "Neural Net",
]

classifiers = [
    LogisticRegression(),
    make_pipeline(PolynomialFeatures(3), LogisticRegression()),
    SVC(kernel="linear", C=0.025),
    SVC(gamma=2, C=1),
    MLPClassifier(alpha=1),
]

# iterate over classifiers
models = []
trained_classifiers = []
for name, clf in zip(names, classifiers):
    scores = []
    for train_indices, test_indices in cv.split(X):
        clf.fit(X[train_indices], y[train_indices].ravel())
        scores.append( clf.score(X_test, y_test.ravel()) )
    
    min_score = min(scores)
    max_score = max(scores)
    avg_score = sum(scores) / len(scores)
    
    trained_classifiers.append(clf)
    models.append((name, min_score, max_score, avg_score))
    
fin_models = pd.DataFrame(models, columns = ['Name', 'Min Score', 'Max Score', 'Mean Score'])

fin_models.sort_values(['Mean Score']).head()

import pickle

svm_model = trained_classifiers[3]

data_path = os.path.join(os.getcwd(), "best-titanic-model.pkl")
pickle.dump(svm_model, open(data_path, 'wb'))