def draw_learning_curves(X, y, estimator, num_trainings):
train_sizes, train_scores, test_scores = learning_curve(
DecisionTreeClassifier,
x2,
y2,
cv=None,
n_jobs=1,
train_sizes=np.linspace(.1, 1.0, num_trainings))
# 训练数据的平均值np,mean 标准差np.std np.mean(train_scores,axis=1)计算每一行的平均值
train_scores_mean = np.mean(train_scores, axis=1)
train_scores_std = np.std(train_scores, axis=1)
test_scores_mean = np.mean(test_scores, axis=1)
test_scores_std = np.std(test_scores, axis=1)
# plt.grid(linestyle=":",color="r") 绘制带刻度线的网格线，linestyle线条风格 color线条颜色
plt.grid()
plt.tytle("learning curve")
plt.xlabe("Training examples")
plt.ylabel("Score")
plt.plot(train_scores_mean, 'o-', color="g", label="Training score")
plt.plot(test_scores_mean, 'o-', color="y", label="Cross-validation score")
plt.legend(loc="best")
plt.show()
#统计一下在qlist 共出现了多少个单词？总共出现了多少个不同的单词
#这里需要做简单的分词，英文用空格
qlist, alist = read_corpus(qa_corpus_path)
q_dict = get_dict(qlist)
word_total_q = sum(q_dict.values())
n_distinctive_words_q = len(q_dict)
print('There are {} words and {} distinctive tokens in question texts'.format(
word_total_q, n_distinctive_words_q))
print(word_total_q)
#todo :统计一下qlist中每个单词出现频率，并把这些频率排一下序
#使用matplotlib里的plot函数，y是词频
plt.bar(np.arange(10000), list(q_dict.value())[100:10100])
plt.ylabe('Frequency')
plt.xlabe('Word Order')
plt.title('Word Frequencies of the Question Corpus')
plt.show()
a_dict = get_dict(alist)
print('The 10 frequentist words in question list (qlist) are :\n{}'.format(
'|'.join(get_topk(10, q_dict))))
class TextNormalizer:
def __init__(self, stopwords, filter_vocab, re_cleaners):
self.lemmatizer = WordNetLemmatizer()
self.filter_vocab = filter_vocab
self.stopwords = stopwords
self.re_cleaners = re_cleaners
print(len(X), len(y))
X_train, X_test, y_train, y_test = model_selection.train_test_split(
X, y, test_size=0.2)
clf = LinearRegression()
clf.fit(X_train, y_train)
accuracy = clf.score(X_test, y_test)
#print(accuracy)
forecast_set = clf.predict(X_lately)
print(forecast_set, accuracy, forecast_out)
last_date = df.iloc[-1].name
last_unix = last_date.to_datetime()
last_unix = time.mktime(last_unix.time_tuple())
one_day = 86400
next_unix = last_unix + one_day
for i in forecast_set:
next_date = datetime.datetime.fromtimestamp(next_unix)
next_unix += one_day
df.loc[next_date] = [np.nan for _ in range(len(df.coloumns) - 1)] + [i]
df['adj_close'].plot()
df['Forecast'].plot()
plt.legend(loc=4)
plt.xlabe('Date')
plt.ylabel('Price')
plt.show()
plt.show()
#visulaisng the test set results
from matplotlib.colors import ListedColormap
X_set, Y_set = X_test, Y_test
X1, X2 = np.meshgrid(
np.arange(start=X_set[:, 0].min() - 1,
stop=X_set[:, 0].max() + 1,
step=0.01),
np.arange(start=X_set[:, 1].min() - 1,
stop=X_set[:, 1].max() + 1,
step=0.01))
plt.contourf(X1,
X2,
classifier.predict(np.array([X1.ravel(),
X2.ravel()]).T).reshape(X1.shape),
alpha=0.75,
cmap=ListedColormap(('red', 'green', 'blue')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(Y_set)):
plt.scatter(X_set[Y_set == j, 0],
X_set[Y_set == j, 1],
c=ListedColormap(('red', 'green', 'blue'))(i),
label=j)
plt.xlabe("LD1")
plt.ylabe("LD2")
plt.tiltle("KNN(on training set)")
plt.legend()
plt.show()
inputs = dataset_total[len(dataset_total) - len(dataset_test) -
60:].values #all the inputs of january 2017
inputs = inputs.reshape(-1, 1) # stock minus january
inputs = sc.transform(inputs)
X_test = []
for i in range(60, 80): # test has 20 days
X_test.append(inputs[i - 60:i, 0]) #zero colomn and 60 rows for each day
X_test = np.array(X_test)
X_test = np.reshape(
X_test, (X_test.shape[0], X_test.shape[1], 1)
) #batch size total days, timsteps 60, inputsize #new indicator price of another stock that is dependent
predicted_stock_price = regressor.predict(X_test)
#go back to non scaling the data
predicted_stock_price = sc.inverse_transform(predicted_stock_price)
#using the matplot to plot the data
plt.plot(real_stock_price, color='red',
label='Real Google Stock Price') # data and label to it
plt.plot(predicted_stock_price, color='red',
label='Real Google Stock Price') #data and label to it
plt.title("google stock price prediction") # title
plt.xlabe('Time')
plt.ylabe('google stock price')
plt.legend() # to includ the legend in the char with no input
plt.show()
## we can increased its accurary by changing the scoring method to accuracy or neg_mean_squared_error
for i in range(len(observacion_1)):
distancia = (puntos[i]**2 * np.sin(2 * theta[i])) / g
puntos = puntos[d]
puntos = np.random.choice(puntos, 1000000)
theta = theta[:len(puntos)]
print(len(puntos))
for i in range(len(observacion_2)):
distancia = (puntos[i]**2 * np.sin(2 * theta[i])) / g
puntos = puntos[d]
puntos = np.random.choice(puntos, 1000000)
theta = theta[:len(puntos)]
print(len(puntos))
plt.figure()
plt.xlabe('Velocidad')
plt.ylabel('Probabilidad de la Velocidad')
plt.hist(puntos, 1000, normed=1)
plt.legend()
plt.savefig('Histograma_vel.png')
#making prediction
data_test = pd.read_csv('Google_Stock_Price_Test.csv')
real_result = data_test.iloc[:, 1:2].values
total_data = pd.concat((data_train['Open'], data_test['Open']), axis=0)
inputs = total_data[len(total_data) - len(data_test) - 60:].values
inputs = inputs.reshape(-1, 1)
inputs = sc.transform(inputs)
xtest = []
for i in range(60, 80):
xtest.append(inputs[i - 60:i, 0])
xtest = np.array(xtest)
xtest = np.reshape(xtest, (xtest.shape[0], xtest.shape[1], 1))
prediction = model.predict(xtest)
prediction = sc.inverse_transform(prediction)
plt.plot(real_result, color='red', label='google stock price')
plt.plot(prediction, color='blue', label='predicted result')
plt.title('google stock price prediciton')
plt.xlabe('date')
plt.ylabel('price')
plt.legend()
plt.show()
def plot(x, y):
plt.plot(x, y)
plt.xlabe("Hour interval of releases")
plt.ylabel("Bugs in Interval")
plt.title("Development of Fixes in Hours")
plt.show()
#Feature scaling
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)
sc_y = StandardScaler()
y_train = sc_y.fit_transform(y_train)
#fitting simple linear regression to the training set
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, y_train)
#Predicting the test set result
y_pred = regressor.predict(X_test)
#visualizing the training set result
plt.scatter(X_train, y_train, color = 'red')
plt.plot(X_train, regressor.predict(X_train), color= 'blue')
plt.title('Salary vs Experience (Training set)')
plt.xlabe('Years of Experience')
plt.ylabel('Salary')
plt.show()
#visualizing the test set result
plt.scatter(X_train, y_train, color = 'red')
plt.plot(X_train, regressor.predict(X_train), color= 'blue')
plt.title('Salary vs Experience (Test set)')
plt.xlabe('Years of Experience')
plt.ylabel('Salary')
plt.show()