def histo_datalink(mode,
lambda_val,
attribute,
ci=95,
datalinks=range(0, NUM_DATA_LINK),
save=False):
stats = scalar_stats(scalar_parse(mode, lambda_val))
for u in datalinks:
attr = attribute + '-' + str(u)
bar = stats['mean'][attr]
error = np.array([
bar - stats['ci' + str(ci) + '_l'][attr],
stats['ci' + str(ci) + '_h'][attr] - bar
]).reshape(2, 1)
plt.bar('User ' + str(u),
bar,
yerr=error,
align='center',
alpha=0.95,
ecolor='k',
capsize=7)
# Show graphic
plt.title(attribute + ": " + MODE_DESCRIPTION[mode])
if save:
plt.savefig("histousers_" + attribute + "_" + mode + "_" + lambda_val +
".pdf",
bbox_inches="tight")
plt.clf()
else:
plt.show()
return
def visualize(self):
# Aadesh
fig = plt.figure()
data1 = pd.read_csv("DSBDA.csv", names=['Name'])
data2 = pd.read_csv(self.directory + "/DSBDA.csv", names=['Name'])
df = pd.merge(data1, data2, how='left', indicator='Submitted')
df['Submitted'] = np.where(df.Submitted == 'both', True, False)
# print (df)
y = []
for i in range(df.index.min(), df.index.max() + 1):
if (df['Submitted'][i] == True):
y.append(1)
elif (df['Submitted'][i] == False):
y.append(0)
x = []
x = list(df.index + 1)
barWidth = 0.85
# Create green Bars
plt.bar(x,
y,
color='green',
edgecolor='white',
width=barWidth,
label='On Time')
plt.savefig(self.directory + "/assigenmet1.pdf")
print('Showing Plot')
plt.show()
def plot_stacked_barchart(self, dataframe, sort, title, xlable, ylable,
kurs):
x = []
tutor = []
y = []
for i in dataframe['tutor']:
if i not in tutor:
tutor.append(i)
y.append([])
for i, elem in enumerate(dataframe[sort]):
print(y, elem)
if elem in x:
y[tutor.index(dataframe['tutor'][i])][x.index(elem)] += 1
else:
x.append(elem)
for j, elem2 in enumerate(tutor):
y[j].append(0)
y[tutor.index(dataframe['tutor'][i])][x.index(elem)] += 1
for i, elem in enumerate(y):
plt.bar(range(len(elem)), elem, label=tutor[i])
plt.xlabel(xlable)
plt.ylabel(ylable)
plt.legend(loc="best")
plt.savefig('./PDFcreater/Plots/{}/{}.png'.format(kurs, title))
#plt.show()
# loescht den Plot fuer den Naechsten Plot
plt.clf()
plt.cla()
plt.close()
def print_pred_distrib_figure(filename, bins, histo, dx, J_opt):
assert isinstance(filename, str), 'filename must be a string'
filename = os.path.splitext(filename)[0] + '.png'
matplotlib = _try_import_matplotlib()
if matplotlib is None:
return
else:
from matplotlib import pyplot as plt
figure = plt.figure(figsize=(7, 7))
plt.bar(bins[:-1],
histo[0],
width=dx,
align='edge',
color='blue',
alpha=0.7,
label='neutral')
plt.bar(bins[:-1],
histo[1],
width=dx,
align='edge',
color='red',
alpha=0.7,
label='deleterious')
plt.axvline(x=J_opt, color='k', ls='--', lw=1)
plt.ylabel('distribution')
plt.xlabel('predicted score')
plt.legend()
figure.savefig(filename, format='png', bbox_inches='tight')
plt.close()
plt.rcParams.update(plt.rcParamsDefault)
LOGGER.info(f'Predictions distribution saved to {filename}')
def chartData(data, keyword):
#Takes input of the results of the fts search and the phrase that was searched for
#and creates bar chart of occurences by book for the phrase
from matplotlib import pyplot as plt
import numpy as np
import math
data = sorted(data, key=lambda x: x[1], reverse=True)
info = []#number of occurences
books = []#list of books
for d in data:
info.append(d[1])
b = d[0]
books.append(b[b.find('LIBER'):])#Use only book number for label since name is the same for all books
#create chart
plt.close()
fig = plt.figure()
width = 0.4
ind = np.arange(len(books))
plt.bar(ind, info, width=width)
plt.xticks(ind + width/2., books)
plt.yticks(np.arange(0,max(info)*2,math.ceil(max(info)/5)))
plt.ylabel('Number of Occurences')
plt.xlabel('Books')
plt.title('Occurences of "' + keyword + '" by book in Curtius Rufus (Latin)')
fig.autofmt_xdate()
plt.show(block=False)#display plot, and continue with program
def musicType_plot(rap, randb, classical, indie, pop, df):
plt.figure()
# declaring testing data
xs = [1, 2, 3, 4, 5]
ys = [randb, rap, classical, pop, indie]
# setting range
xrng = np.arange(len(xs))
yrng = np.arange(0, max(ys)+60, 50)
#labeling data
plt.xlabel('Music Type')
plt.ylabel('Music volume')
# spacing and declare bar chart
plt.bar(xrng, ys, 0.45, align="center")
# labeling
plt.xticks(xrng, ["randb", "rap", "classical", "pop", "indie"])
plt.yticks(yrng)
plt.grid(True)
plt.show()
def print_path_prob_figure(filename,
bins,
histo,
dx,
path_prob,
smooth_path_prob,
cutoff=200):
assert isinstance(filename, str), 'filename must be a string'
filename = os.path.splitext(filename)[0] + '.png'
matplotlib = try_import_matplotlib()
if matplotlib is None:
return
else:
from matplotlib import pyplot as plt
figure = plt.figure(figsize=(7, 7))
s = np.sum(histo, axis=0)
v1 = np.where(s >= cutoff, path_prob, 0)
v2 = np.where(s < cutoff, path_prob, 0)
v3 = np.where(s >= cutoff, smooth_path_prob, 0.)
plt.bar(bins[:-1], v1, width=dx, align='edge', color='red', alpha=1)
plt.bar(bins[:-1], v2, width=dx, align='edge', color='red', alpha=0.7)
plt.plot(bins[:-1] + dx / 2, v3, color='orange')
plt.ylabel('pathogenicity prob.')
plt.xlabel('predicted score')
plt.ylim((0, 1))
figure.savefig(filename, format='png', bbox_inches='tight')
plt.close()
plt.rcParams.update(plt.rcParamsDefault)
LOGGER.info(f'Pathogenicity plot saved to {filename}')
def evaluation(X, y, model, n_preds=10, random=True, show_graph=True):
n_steps = X.shape[1]
max_random_int = len(y) - n_steps
y_true, y_pred, prediction_accuracy, slices = [], [], [], []
for i in range(n_preds):
if random == True:
position = np.random.randint(0, max_random_int)
else:
position = i
y_hat = model.predict(X[position:position + 1])[0][0]
y_pred.append(y_hat)
y_true.append(y[position])
y_current = y[position]
# If we predit return, c = 0, else c = previous sequence position
if y.min() < 0:
c = 0
else:
c = y[position - 1]
if ((y_hat > c) & (y_current > c)) or ((y_hat < c) & (y_current < c)):
acc = 1
else:
acc = 0
prediction_accuracy.append(acc)
slices.append((list(y[position - n_steps:position + 1]),
list(y[position - n_steps:position]) + [y_hat], acc))
if show_graph == True:
plt.rcParams['figure.dpi'] = 227
plt.style.use('seaborn-whitegrid')
plt.figure(figsize=(16, 6))
plt.bar(range(n_preds),
y_true[:],
width=.7,
alpha=.6,
color="#4ac2fb",
label="True")
plt.bar(range(n_preds),
y_pred[:],
width=.7,
alpha=.6,
color="#ff4e97",
label="Predicted")
plt.axhline(0, color="#333333", lw=.8)
plt.legend(loc=1)
plt.title('Daily Return Prediction', fontSize=15)
plt.show()
print('MSE:', mean_squared_error(y_true, y_pred))
print('Accuracy: {}%'.format(
round((sum(prediction_accuracy) / len(prediction_accuracy)) * 100), 2))
return slices, np.array(y_true), np.array(y_pred)
def char_positive():
x_axis = Category
y_axis = statistic_positive()
y_pos = np.arange(len(y_axis))
plt.figure(figsize=(10, 5))
plt.bar(y_pos, y_axis)
plt.xticks(y_pos, x_axis)
plt.title('What categories we choose the most')
plt.show()
def plot_boring_barchart(self,dataframe,x,y,title,xlable,ylable, kurs):
plt.bar(x, y, color='blue')
#plt.title(title)
plt.xlabel(xlable)
plt.ylabel(ylable)
plt.savefig('./PDFcreater/Plots/{}/{}.png'.format(kurs,title))
#loescht den Plot fuer den Naechsten Plot
plt.clf()
plt.cla()
plt.close()
def getHistogramPGN(df):
y = df.iloc[:, -1]
perc_win = y.sum() / y.count()
height = [1 - perc_win, perc_win]
bars = ('win=0 (%)', 'win=1 (%)')
y_pos = np.arange(len(bars))
plt.bar(y_pos, height)
plt.xticks(y_pos, bars)
plt.title("labels histogram")
path = WORKING_PATH + "/___histogram.png"
plt.savefig(path)
return path
def _plot_lengths(self, lens, prec, figsize):
'''Plots a list of file lengths displaying prec digits of precision'''
rounded = [round(i, prec) for i in lens]
rounded_count = Counter(rounded)
plt.figure(num=None, figsize=figsize, dpi=80, facecolor='w', edgecolor='k')
labels = sorted(rounded_count.keys())
values = [rounded_count[i] for i in labels]
width = 1
plt.bar(labels, values, width)
xticks = np.linspace(int(min(rounded)), int(max(rounded))+1, 10)
plt.xticks(xticks)
plt.show()
def plot_hist(a,b):
v = np.random.beta(a, b, 10000)
s = np.zeros(v.shape[0])
for i in range(v.shape[0]):
s[i] = np.random.binomial(20,v[i])
figure()
center = scipy.stats.itemfreq(s)[:,0]
hist = scipy.stats.itemfreq(s)[:,1]
plt.bar(center, hist, align = 'center', width = 0.7)
plt.savefig('../Figures/a'+str(a)+'_b'+str(int(b))+'.pdf')
def plot_hist(a, b):
v = np.random.beta(a, b, 10000)
s = np.zeros(v.shape[0])
for i in range(v.shape[0]):
s[i] = np.random.binomial(20, v[i])
figure()
center = scipy.stats.itemfreq(s)[:, 0]
hist = scipy.stats.itemfreq(s)[:, 1]
plt.bar(center, hist, align='center', width=0.7)
plt.savefig('../Figures/a' + str(a) + '_b' + str(int(b)) + '.pdf')
def plotDisparityHistogram(network=None):
assert network is not None, "Network is not initialised! Visualising failed."
import matplotlib.pyplot as plt
from NetworkBuilder import sameDisparityInd
spikesPerDisparityMap = []
for d in range(0, maxDisparity-minDisparity+1):
cellsOut = [network[x][1] for x in sameDisparityInd[d]]
spikesPerDisparityMap.append(sum([sum(x.get_spike_counts().values()) for x in cellsOut]))
print spikesPerDisparityMap
plt.bar(range(0, maxDisparity-minDisparity+1), spikesPerDisparityMap, align='center')
plt.show()
def _Learning(descriptor_list, n_clusters, n_images, train_labels, ret=None, std=None):
#set up model
kmeans_obj = KMeans(n_clusters=n_clusters)
#format the data (descriptor list)
vStack = np.array(descriptor_list[0])
for remaining in descriptor_list[1:]:
vStack = np.vstack((vStack, remaining))
descriptor_vstack = vStack.copy()
#perform clustering
kmeans_ret = kmeans_obj.fit_predict(descriptor_vstack)
#develop vocabulary
mega_histogram = np.array([np.zeros(n_clusters) for i in range(n_images)])
old_count = 0
for i in range(n_images):
l = len(descriptor_list[i])
for j in range(l):
if ret is None:
idx = kmeans_ret[old_count+j]
else:
idx = ret[old_count+j]
mega_histogram[i][idx]+=1
old_count+=1
#display trained vocabulary
vocabulary = mega_histogram
x_scaler = np.arange(n_clusters)
y_scalar = np.array([abs(np.sum(vocabulary[:,h], dtypes=np.int32)) for h in range(n_clusters)])
plt.bar(x_scaler,y_scalar)
plt.xlabel("Visual Word Index")
plt.ylabel("Frequency")
plt.title("Complete Vocabulary Generated")
plt.xticks(x_scaler+0.4,x_scaler)
plt.show()
#standardize
if std is None:
scale = prep.StandardScaler().fit(mega_histogram)
mega_histogram = scale.transform(mega_histogram)
else:
mega_histogram = std.transform(mega_histogram)
#train--USES SVC!!
clf = SVC()
self.clf.fit(mega_histogram,train_labels)
def color_info(color_dist, inner_deck_list):
color_dict = color_dist(inner_deck_list, "deck")
print("colors:")
pp.pprint(color_dict)
fig, ax = plt.subplots()
ax.set_xlabel('Colors')
ax.set_ylabel('Count')
ax.set_title('Distribution of Colored cards in deck')
x_val = []
y_val = []
for i in color_dict.items():
x_val.append(i[0])
y_val.append(i[1])
plt.bar(x_val, y_val)
plt.show()
def myplot(feat, i, j, df):
df = df[i:j + 1]
df = df[df["rate"] > 3.8]
n = df[feat].value_counts()
l = list(zip(list(n), list(n.keys())))
l.sort(key=lambda tup: tup[1])
height = [x[0] for x in l]
bars = [x[1] for x in l]
y_pos = np.arange(len(bars))
plt.bar(y_pos, height, color=sns.color_palette())
plt.xticks(y_pos, bars, rotation="vertical")
plt.xlabel("Suitable values")
plt.ylabel("Count")
plt.title("Values for " + feat)
plt.show()
def fnctn(a,c):
df2 = pd.DataFrame(data.groupby(a)[c].count())
df2=df2.astype(float)
plot1 = plt.bar(x=df2.index,y=df2.iloc[:,0])
plot1.set_xticklabels(plot1.get_xticklabels(), rotation=30, fontsize=6)
plot1.figure.savefig("./static/q18.jpg")
plt.close()
def draw_bar(savename):
import matplotlib.pyplot as plt
size = 3
x = np.arange(size)
a = [34.89, 33.87, 72.37]
b = [551.72, 552.87, 698.34]
xl = ['training time \n on MNIST', 'training time on \n Fashion-MNIST', 'training time \n on CIFAR-10']
total_width, n = 0.54, 2
width = total_width / n
x = x - (total_width - width)
plt.figure()
plt.bar(x, a, width=width)
plt.bar(x + width, b, width=width)
plt.ylabel('time(s)')
plt.xticks(x, xl,)
plt.legend()
plt.savefig('../eps/' + savename)
plt.show()
def print_feat_imp_figure(filename, feat_imp, featset):
assert isinstance(filename, str), 'filename must be a string'
filename = os.path.splitext(filename)[0] + '.png'
matplotlib = _try_import_matplotlib()
if matplotlib is None:
return
else:
from matplotlib import pyplot as plt
fig = plt.figure(figsize=(7, 7))
n = len(feat_imp)
plt.bar(range(n), feat_imp, align='center', tick_label=featset)
plt.xticks(rotation='vertical')
plt.ylabel('feat. importance')
fig.savefig(filename, format='png', bbox_inches='tight')
plt.close()
plt.rcParams.update(plt.rcParamsDefault)
LOGGER.info(f'Feat. importance plot saved to {filename}')
def drawTKY():
"""
Function plots 10 most popular Venue Categories in Tokyo.
"""
#Import dataset of New York from root directory
TKY = pd.read_csv('dataset_TSMC2014_TKY.csv')
TKY=TKY[["venueCategory","venueCategoryId"]]
grouped2=TKY.groupby(["venueCategory"]).count()
grouped2=grouped2.sort_values('venueCategoryId')
grouped2=grouped2[237:247]
#Plot bars of most popular venue categories
plt.figure(figsize=(16,6))
plt.style.use('fivethirtyeight')
plt.bar(grouped2.index,grouped2["venueCategoryId"])
plt.title("10 Most Popular Venue Categories \n Tokyo: 2012-2013",fontsize=14,color='black')
plt.ylabel("Check-ins per Venue Category",fontsize=14)
plt.show()
def drawNYC():
"""
Function plots 10 most popular Venue Categories in New York.
"""
#Import dataset of New York from root directory
NYC = pd.read_csv('dataset_TSMC2014_NYC.csv')
NYC=NYC[["venueCategory","venueCategoryId"]]
grouped=NYC.groupby(["venueCategory"]).count()
grouped=grouped.sort_values('venueCategoryId')
grouped=grouped[241:251]
#Plot bars of most popular venue categories
plt.figure(figsize=(16,6))
plt.style.use('fivethirtyeight')
plt.bar(grouped.index,grouped["venueCategoryId"])
plt.title("10 Most Popular Venue Categories \n New York: 2012-2013",fontsize=14,color='black')
plt.ylabel("Check-ins per Venue Category",fontsize=14)
plt.show()
def visual_importnance(X, forest):
importances = forest.feature_importances_
std = np.std([tree.feature_importances_ for tree in forest.estimators_],
axis=0)
indices = np.argsort(importances)[::-1]
# Print the feature ranking
print("Feature ranking:")
for f in range(X.shape[1]):
print("%d. feature %d (%f)" % (f + 1, indices[f], importances[indices[f]]))
# Plot the feature importances of the forest
plt.figure()
plt.title("Feature importances")
plt.bar(range(X.shape[1]), importances[indices],
color="r", yerr=std[indices], align="center")
plt.xticks(range(X.shape[1]), indices)
plt.xlim([-1, X.shape[1]])
plt.show()
def sunSat_plot(saturday_mean, sunday_mean, df):
plt.figure()
# declaring values to be plotted
xs = [1, 2]
ys = [saturday_mean, sunday_mean]
# setting range
xrng = np.arange(len(xs))
yrng = np.arange(0, max(ys)+50, 50)
# making bar chart and alligning items properly
plt.bar(xrng, ys, 0.45, align="center")
# labeling
plt.xticks(xrng, ["Saturday", "Sunday"])
plt.yticks(yrng)
plt.grid(True)
plt.show()
def make_hists(self, X, y):
colors = [
'red', 'tan', 'lime', 'orange', 'black', 'yellow', 'green', 'pink',
'red', 'brown', 'grey', 'purple', 'navy'
]
features = (set(self.train_df.keys()) -
{'Vote'}) - set(categorical_features)
for feature in features:
df = pd.DataFrame({
"x": X[feature].values,
"class": y.values.flatten()
})
_, edges = np.histogram(df["x"], bins=15)
histdata = []
labels = []
for n, group in df.groupby("class"):
histdata.append(np.histogram(group["x"], bins=edges)[0])
labels.append(n)
hist = np.array(histdata)
histcum = np.cumsum(hist, axis=0)
plt.bar(edges[:-1],
hist[0, :],
width=np.diff(edges)[0],
label=labels[0],
align="edge")
for i in range(1, len(hist)):
plt.bar(edges[:-1],
hist[i, :],
width=np.diff(edges)[0],
bottom=histcum[i - 1, :],
color=colors[i],
label=labels[i],
align="edge")
plt.legend(title="class")
plt.savefig('hists_label/' + feature + '.jpeg')
def scree_plot(self):
total = sum(self.eig_vals)
explained_var = [(i / total) * 100
for i in sorted(self.eig_vals, reverse=True)]
cum_var = np.cumsum(explained_var)
with plt.style.context('seaborn-darkgrid'):
plt.bar(range(len(explained_var)),
explained_var,
align='center',
label='individual explained variance')
plt.step(range(len(explained_var)),
cum_var,
where='mid',
label='cumulative explained variance',
color="red")
plt.ylabel("Cumulative variance")
plt.xlabel("Principal components")
plt.tight_layout()
plt.legend(loc='best')
plt.show()
def plotAmod(self):
# Set up state space (FSM1,2,3, Loc and Vel)
x_val = [1, 2, 3, 4, 5]
y_val = [
self.FSM1_elapsed, self.FSM2_elapsed, self.FSM3_elapsed,
self.Loc_elapsed, self.Vel_elapsed
]
# Compare separate states (MECE) and wheels active/non-active
y_label = [
'Intersection Active', 'State Estimator Active',
'Indefinite Navigation Active', 'Localization Active',
'Wheels Active'
]
# Plot values upon shutdown
plt.bar(x_val,
y_val,
tick_label=y_label,
width=0.5,
color=['blue', 'green'])
plt.xlabel('Duckiebot states')
plt.ylabel('Duration (s)')
plt.title('Time spent by %s per state' % self.veh_name)
def plot_value_array(i, predictions_array, true_label, number_of_classes=3):
predictions_array, true_label = predictions_array, true_label[i]
plt.style.use(['classic'])
plt.grid(False)
plt.xticks(range(number_of_classes))
plt.yticks([])
thisplot = plt.bar(range(number_of_classes), 1, color="#FFFFFF")
plt.ylim([0, 1])
predicted_label = np.argmax(predictions_array)
#print(true_label[0])
#print(predicted_label)
thisplot[predicted_label].set_color('red')
thisplot[true_label].set_color('blue')
def make_bar_graph(data=housing):
'''
:param data:
:return:
'''
data = data
mp.figure('Bar', facecolor='lightgray')
mp.title('Bar', fontsize=20)
gs = mg.GridSpec(3, 4)
i, j = 0, 0
for column in housing.columns:
# 创建子图
mp.subplot(gs[i, j])
# 在图形内部添加文字，设置位置，内容，对齐方式，字号，颜色，透明度
mp.text(0.5, 0.5, str(i) + '+' + str(j), ha='center', va='center', size=35, color='red', alpha=0.5)
# 删除边界刻度
mp.xticks(())
mp.yticks(())
# 绘制柱状图
single_data = housing[column]
min_data, max_data = min(single_data), max(single_data)
mp.xlim(min(min_data, max_data))
step = (max_data - min_data) / 10
for x in range(min_data, max_data, step):
sum_num = sum(x <= single_data <= x + step)
y.append(sum_num)
x = np.range(len(y))
mp.bar(x, y, 0.4, color='dodgerblue', label=column, alpha=0.75)
# 调整子图位置
j += 1
j = j % 4
i = i + j // 4
# 改变布局形式，改为紧凑布局
mp.tight_layout()
pass
def musicCategory_plt(randb_ser, rap_ser, classical_ser, pop_ser, indie_ser,df):
plt.figure()
# define x and y values
xs = [1, 2, 3, 4, 5]
ys = [len(randb_ser), len(rap_ser), len(classical_ser), len(pop_ser), len(indie_ser)]
# setting range
xrng = np.arange(len(xs))
yrng = np.arange(0, max(ys)+60, 50)
# labeling data
plt.xlabel('Music Type')
plt.ylabel('Days listened')
# define bar chart and spacing
plt.bar(xrng, ys, 0.45, align="center")
# more labeling
plt.xticks(xrng, ["randb", "rap", "classical", "pop", "indie"])
plt.yticks(yrng)
plt.grid(True)
plt.show()
def plot_response_time_variousT():
dataframe = pd.DataFrame()
index = []
for k in capacity_change_time:
for mode in modes:
index.append(f"{mode},t={k}s")
dataframe['index'] = index
for mode in modes:
index = []
meanResponseTime = []
for i in capacity_change_time:
df = scalar_df_parse(
f"C:\\Users\\Leonardo Poggiani\\Documents\\GitHub\\PECSNproject\\csv\\pool_classico_varia_T\\{mode}{i}.csv"
)
response = df[df.name == "responseTime"]
meanResponseTime.append(response.value.mean())
index.append(i)
plt.bar(index, meanResponseTime)
plt.title(f"{mode}")
plt.rcParams["figure.figsize"] = (12, 10)
plt.xticks(rotation=25)
plt.show()
plt.xlabel("Value of t")
plt.ylabel("Response time")
plt.title("Comparison of various values of t")
plt.legend(loc='best')
plt.savefig(
"C:\\Users\\Leonardo Poggiani\\Documents\\GitHub\\PECSNproject\\analysis\\variandoT\\responseTimeAlVariareDiT2.png"
)
fig = plt.pyplot.gcf()
fig.set_size_inches(16, 10)
count_by_occupation = user_fields.map(lambda fields: (fields[3], 1)).reduceByKey(lambda x, y: x + y).collect()
x_axis1 = np.array([c[0] for c in count_by_occupation])
y_axis1 = np.array([c[1] for c in count_by_occupation])
x_axis = x_axis1[np.argsort(y_axis1)]
y_axis = y_axis1[np.argsort(y_axis1)]
pos = np.arange(len(x_axis))
width = 1.0
ax = plt.axes()
ax.set_xticks(pos + (width / 2))
ax.set_xticklabels(x_axis)
plt.bar(pos, y_axis, width, color='lightblue')
plt.xticks(rotation=30)
fig = plt.pyplot.gcf()
fig.set_size_inches(16, 10)
count_by_occupation2 = user_fields.map(lambda fields: fields[3]).countByValue()
print "Map-reduce approach:"
print dict(count_by_occupation2)
print ""
print "countByValue approach:"
print dict(count_by_occupation)
'''
explore movie data
'''
import matplotlib as plt
import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
import datetime
Data = pd.read_csv("wikipedia_by_month.txt", sep='\t', header = None, names=['Date', 'Count'])
fig = plt.figure()
ind = np.arange(len(Data['Date']))
plt.bar(ind, Data['Count'])
fig.autofmt_xdate()
plt.xticks(ind, Data['Date'], rotation = 'vertical')
plt.savefig("figure.pdf")
