def plot_res(bm_fname, optz_cfg=None, plot_cfg=None):
# load bm_fname
bm = importlib.import_module(bm_fname.rsplit('.', 1)[0])
e = bm.e; decorate_stind(e)
compare = bm.compare
if optz_cfg is None: optz_cfg = bm.optz_cfg
if plot_cfg is None: plot_cfg = bm.plot_cfg
# {optz,plot}_detail
optz_detail = get_optz_detail(bm_fname, optz_cfg)
plot_detail = get_plot_detail(bm_fname, optz_cfg, plot_cfg)
print('\n===== PLOT: %s =====' % plot_detail)
# load res's from files
thts_res_l = []
alg_str_l = []
for alg_str in compare:
thts_res = load_res(optz_detail, alg_str)
thts_res = [(t,thts) for (t,thts,_,_,_) in thts_res]
thts_res_l += [thts_res]
alg_str_l += [alg_str]
# plot & save graph
plot_fname = '%s%s' % (plot_detail, PLOT_EXT)
text_fname = plot_fname[:-len(PLOT_EXT)] + RES_EXT
objc_func = lambda thts, e=e: elbo_val.elbo_val(e, thts,
sample_n = plot_cfg['sample_n'])
util.plot_graph(thts_res_l, objc_func,
plot_fname = plot_fname,
text_fname = text_fname,
legend_l = alg_str_l,
step = plot_cfg['step'])
def registry(filename,nf, ptitle, kfstart=2, kfend=5, kstart=1, kend=5): ''' starts the project. For each fold it calculates mean accuracy, standard deviation and plot the corresponding graph. ''' dataset = load_dataset(filename) kf_accuracy = [] for kf in range(kfstart, kfend+1): kf_accuracy.append(get_Allknn_acc_for_kfold(dataset, kf, kstart, kend, nf)) kf_mean_acc = [sum(acclist)/len(acclist) for acclist in kf_accuracy] sd = [numpy.std(acclist) for acclist in kf_accuracy] for kf, acclist in zip(range(kfstart, kfend+1),kf_accuracy): print kf, "fold validation ===> accuracy of", sum(acclist)/len(acclist) # print kf_mean_acc mean_sd = sum(sd)/len(sd) mean_acc = sum(kf_mean_acc)/len(kf_mean_acc) print "Mean accuracy : ", mean_acc print "Mean S.D : ", mean_sd plot_graph(kf_accuracy, kstart, kend,sd, ptitle)
def registry(filename, nf, ptitle, kfstart=2, kfend=5, kstart=1, kend=5):
''' starts the project. For each fold it calculates mean accuracy,
standard deviation and plot the corresponding graph.
'''
dataset = load_dataset(filename)
kf_accuracy = []
for kf in range(kfstart, kfend + 1):
kf_accuracy.append(
get_Allknn_acc_for_kfold(dataset, kf, kstart, kend, nf))
kf_mean_acc = [sum(acclist) / len(acclist) for acclist in kf_accuracy]
sd = [numpy.std(acclist) for acclist in kf_accuracy]
for kf, acclist in zip(range(kfstart, kfend + 1), kf_accuracy):
print kf, "fold validation ===> accuracy of", sum(acclist) / len(
acclist)
# print kf_mean_acc
mean_sd = sum(sd) / len(sd)
mean_acc = sum(kf_mean_acc) / len(kf_mean_acc)
print "Mean accuracy : ", mean_acc
print "Mean S.D : ", mean_sd
plot_graph(kf_accuracy, kstart, kend, sd, ptitle)
X_test, y_test = convert_to_nn_input(predict_df,
look_back=look_back,
look_forward=look_forward)
model = Sequential()
model.add(LSTM(10, input_shape=(look_back * no_of_features, 1)))
model.add(Dense(1, activation='relu'))
model.compile(optimizer='adam', loss='mse')
X_train = X_train.reshape((X_train.shape[0], X_train.shape[1], 1))
X_test = X_test.reshape((X_test.shape[0], X_test.shape[1], 1))
history = model.fit(X_train,
y_train,
epochs=100,
validation_data=(X_test, y_test),
shuffle=False)
y_test_predictions = model.predict(X_test)
# Calculate the RMSE and MAE between ground truth and predictions and
# add to the CSV file
rmse_val = mean_squared_error(y_test, y_test_predictions)**0.5
mae_val = mean_absolute_error(y_test, y_test_predictions)
csv_file.add_row(
[company_name, regressor_name,
str(rmse_val),
str(mae_val)])
# Plot the graph comparing ground truth with predictions
plot_graph(y_test, y_test_predictions, [i for i in range(len(y_test))],
directory + company_name + "_" + regressor_name + ".png")
# A large batch size of 64 reviews is used to space out weight updates.
history = model.fit(X_train,
y_train,
batch_size=64,
epochs=3,
verbose=1,
validation_data=(X_test, y_test))
# Evaluation of the model with training data
scores_train = model.evaluate(X_train, y_train, verbose=0)
print("Training Data: ")
print(
"Accuracy: %.2f%%, F_1Score: %.2f%% , Precision: %.2f%%, Recall: %.2f%% " %
(scores_train[1] * 100, scores_train[2] * 100, scores_train[3] * 100,
scores_train[4] * 100))
# Evaluation of the model with test data
scores = model.evaluate(X_test, y_test, verbose=0)
print("Test Data:")
print(
"Accuracy: %.2f%%, F_1Score: %.2f%% , Precision: %.2f%%, Recall: %.2f%%" %
(scores[1] * 100, scores[2] * 100, scores[3] * 100, scores[4] * 100))
if PLOT_GRAPH:
plot_graph(history)
if PLOT_MODEL:
img_file = 'model_diagrams/cnn.png'
keras.utils.plot_model(model,
to_file=img_file,
show_shapes=True,
show_layer_names=True)
x_vals = np.array([1.1, 2.2, 3.3, 4.4]).astype(np.float)
y_vals = np.array([5.5, 6.6, 7.7, 8.8]).astype(np.float)
# read files
pass
# create plots
# implementations in boolean flag to prevent interactive plots
if False:
util.plot_normal(0, 1)
if True:
X_range = np.array(range(0, len(x_vals)))
plot1 = util.getYPlotObj(x_vals, "line", "X1", "red")
plot2 = util.getYPlotObj(y_vals, "scatter", "X2", "green")
util.plot_graph(X_range, [plot1, plot2], showLegend=True)
# getStats
[x_mean, x_var, x_min, x_max] = util.getStats(x_vals)
[x_mean, x_var, x_min, x_max] = util.getStats(x_vals, printStats=True)
# tests
result = util.walds_test_2_population(x_vals, y_vals, thres=1.962)
result = util.paired_t_test(x_vals, y_vals, thres=1.962)
result = util.permutation_test(x_vals, y_vals, thres=1.962)
# time series
[average_error, errors, predictions] = util.make_predictions(x_vals,
method="ewma",
ewma_factor=0.5)
# [average_error, errors, predictions] = util.make_predictions(x_vals, method="seasonal", season_factor=2)
spearman_connectivity,
community_alg=c_a,
thresh_func=t_f,
reorder=True,
threshold=t,
layout='circle',
plot_threshold=plot_t,
print_options={'lookup': {}},
plot_options={'inline': False})
subgraph = community_reorder(get_subgraph(G_w, 3))
print_community_members(subgraph)
subgraph_visual_style = get_visual_style(subgraph,
vertex_size='eigen_centrality')
plot_graph(subgraph,
visual_style=subgraph_visual_style,
layout='circle',
inline=False)
#**********************************
# Threshold and Stability Analysis
#**********************************
# plot number of communities as a function of threshold
thresholds = np.arange(.15, .35, .01)
partition_distances = []
cluster_size = []
for t in thresholds:
# simulate threhsold 100 times
clusters = simulate(100,
fun=lambda: Graph_Analysis(
corr_data, threshold=t, weight=True, display=False)
