day = rowdata.day
date = {}
for i in range(len(year)):
da = f'{year[i]}-{month[i]}-{day[i]}'
if da not in date.keys():
date[da] = 1
else:
date[da] += 1
points = [(key, value) for key, value in date.items()][::-1]
gd_lr = LinearRegression()
x_ = [float(time.mktime(time.strptime(x[0], "%Y-%m-%d"))) for x in points]
y_ = [float(y[1]) for y in points]
gd_lr.fit(np.array(x_)[:, np.newaxis], np.array(y_))
x_axis = [time.strftime("%Y-%m-%d", time.localtime(i)) for i in x_]
print(x_axis[::18])
plt.rcParams['font.sans-serif'] = ['simhei'] #设置字体
plt.figure(figsize=[12, 8])
plt.title('回归模型')
plt.scatter(x_axis, y_, alpha=0.4, edgecolors='white')
#plt.xticks(range(7), [2013,2014,2015,2016,2017,2018,2019])
#plt.yticks(y_, fontsize=9)
plt.plot(x_axis, gd_lr.predict(np.array(x_)[:, np.newaxis]), color='gray')
ax = plt.gca()
ax.spines['right'].set_color('none')
ax.spines['top'].set_color('none')
xmajorLocator = LinearLocator(10)
ax.xaxis.set_major_locator(xmajorLocator)
plt.show()
# X_train, X_test, y_train, y_test
file_name = filename[70:]
file_name = file_name.replace(".csv", "")
# print file_name
# print reg.w_
print 'Intercept: %.2f' % reg.b_
print 'Slope: %.2f\n' % reg.w_[0]
filenames.append(file_name)
intercepts.append(reg.b_)
slopes.append(reg.w_)
plt.scatter(X, y, c='blue')
plt.plot(X, reg.predict(X), color='red')
plt.show()
# mult_index_X_train = mult_index[:-15]
# mult_index_X_test = mult_index[-20:]
# mult_month_count_y_train = mult_month_count[:-15]
# mult_month_count_y_test = mult_month_count[-20:]
# lm = LinearRegression()
# lm.fit(mult_index_X_train, mult_month_count_y_train)
# mult_month_count_y_pred = lm.predict(mult_index_X_test)
# plt.scatter(mult_index_X_test, mult_month_count_y_pred, color='blue', linewidth=3)
# plt.show()
print(set_sizes[0])
print('here', set_sizes[nrows] * 0.7)
X_train = X.head(int(set_sizes[nrows] * 0.7))
X_test = X.tail(int(set_sizes[nrows] * 0.3))
Y_train = Y.head(int(set_sizes[nrows] * 0.7))
Y_test = Y.tail(int(set_sizes[nrows] * 0.3))
ne_lr = LinearRegression(minibatches=None)
Y2 = pd.to_numeric(Y, downcast='float')
print("here", type((Y2)))
print(type(Y_train))
ne_lr.fit(X_train, pd.to_numeric(Y_train, downcast='float'))
print(ne_lr)
y_pred = ne_lr.predict(X_test)
res = mean_squared_error(Y_test, y_pred)
#res = scoring(y_target=Y_test, y_predicted=y_pred, metric='rmse')
print("results: ", res)
lin = linear_model.LinearRegression()
lin.fit(X_train, Y_train)
predictedCV = cvp(lin, X, Y, cv=10)
print("rmse cross val", mean_squared_error(Y, predictedCV))
X = np.asanyarray(x).reshape(
-1, 1
) #x need to be converted into matrix without changing the array values to fit the model
eta1 = 0.0001
eta2 = 0.1
from mlxtend.regressor import LinearRegression
from sklearn import metrics
ada1_bgd = LinearRegression(method='sgd',
eta=eta1,
epochs=20,
random_seed=0,
minibatches=1) #for adalline bgd
ada1_bgd.fit(X, y)
y_pred = ada1_bgd.predict(X)
mse1 = metrics.mean_squared_error(y_pred, y)
ada2_bgd = LinearRegression(method='sgd',
eta=eta2,
epochs=20,
random_seed=0,
minibatches=1) #for adaline bgd
ada2_bgd.fit(X, y)
y_pred = ada2_bgd.predict(X)
mse2 = metrics.mean_squared_error(y_pred, y)
print("Adaline Batch Gradient Descent Regression Algorithm")
print("-----------------------------------------------------")
print("\tLearning Rate: ", eta1, "\t\t\tLearning Rate: ", eta2)
print('\tIntercept: %.2f' % ada1_bgd.w_, end='')
print('\t\t\t\tIntercept: %.2f' % ada2_bgd.w_)
print('\tSlope: %.2f' % ada1_bgd.b_, end='')
