def plot_exponent(series, ax, num_of_bins, color, label):
x_series, p_series = getDistribution(series, True)
bx_series, bp_series, bp_series_err = getBinnedDistribution(
x_series, p_series, num_of_bins)
ax.plot(x_series, p_series, color + 'o', alpha=0.1, markersize=7)
ax.errorbar((bx_series[1:] + bx_series[:-1]) / 2,
bp_series,
yerr=bp_series_err,
color=color,
fmt='o-',
alpha=0.9,
capsize=3,
elinewidth=1,
linewidth=3,
label=label)
def plot_measure(average_ratings_year,
title,
num_of_bins,
ax,
color,
label,
music=False):
x_average_ratings_year, y_average_ratings_year, yerr_average_ratings_year = get_yearly_avg_data(
average_ratings_year)
bx_average_ratings_year, bp_average_ratings_year, bperr_average_ratings_year = getBinnedDistribution(
x_average_ratings_year, y_average_ratings_year, num_of_bins)
ax.set_title(title, fontsize=20)
if music:
ax.errorbar(x_average_ratings_year,
y_average_ratings_year,
yerr=yerr_average_ratings_year,
fmt=color + '-',
alpha=0.5,
capsize=3,
elinewidth=1,
linewidth=2)
ax.errorbar(
(bx_average_ratings_year[1:] + bx_average_ratings_year[:-1]) / 2,
bp_average_ratings_year,
yerr=bperr_average_ratings_year,
fmt=color + 'o-',
alpha=0.6,
capsize=3,
elinewidth=1,
linewidth=3,
label=label)
else:
ax.errorbar(
(bx_average_ratings_year[1:] + bx_average_ratings_year[:-1]) / 2,
bp_average_ratings_year,
yerr=bperr_average_ratings_year,
fmt=color + 'o-',
alpha=0.6,
capsize=3,
elinewidth=1,
linewidth=3,
label=label)
ax.set_xlim([1880, 2020])
def plot_ccdf(file_avg_all, num_of_bins, ax, color, label, Nmin, title,
marker):
x_Nstar_avg_all, p_Nstar_avg_all, len_career, r_square, numInd = parse_N_star_N_data(
file_avg_all, Nmin)
if 'orig' in label:
ax.set_title(str(numInd) + ' ' + title, fontsize=19)
bx_average_ratings, bp_average_ratings, bperr_average_ratings = getBinnedDistribution(
np.asarray(x_Nstar_avg_all), np.asarray(p_Nstar_avg_all), num_of_bins)
#ax.plot(x_Nstar_avg_all, p_Nstar_avg_all, color = color, marker = 'o', linewidth = 0, markersize = 5, alpha= 0.5, label = label + ', ' + str(len_career) + ' $R^2=$' + str(round(r_square, 4)),)
ax.errorbar((bx_average_ratings[1:] + bx_average_ratings[:-1]) / 2,
bp_average_ratings,
yerr=bperr_average_ratings,
fmt=color + '-',
linewidth=1,
markersize=9,
label=label + ' $R^2 = $' + str(round(r_square, 5)),
marker=marker,
alpha=0.7)
return r_square
def get_r_model_curves(data_file,
max_data_file,
ax,
label,
num_of_bins,
title,
xlabel,
ylabel,
log=False):
ax.set_title(title, fontsize=19)
ax.set_xlabel(xlabel, fontsize=17)
ax.set_ylabel(ylabel, fontsize=17)
data = [float(line.strip()) for line in open(data_file)]
(data_max,
career_len) = zip(*[[float(num) for num in line.strip().split('\t')]
for line in open(max_data_file) if 'nan' not in line])
ax.plot(career_len,
data_max,
marker='o',
color='lightgrey',
alpha=0.15,
linewidth=0)
career_max = []
career_max_dict = {}
for i in range(100):
data_new = data[:]
random.shuffle(data_new)
for leng in career_len:
#career_max.append(max( data_new[0:int(leng)]))
if leng not in career_max_dict:
career_max_dict[leng] = [max(data_new[0:int(leng)])]
else:
career_max_dict[leng].append(max(data_new[0:int(leng)]))
del data_new[0:int(leng)]
sorted_len = sorted(list(set(career_len)))
career_max = []
for s in sorted_len:
career_max.append(np.mean(career_max_dict[s]))
print len(sorted_len), len(career_max)
if not log:
xb_data, pb_data, pberr_data = getBinnedDistribution(
np.asarray(career_len), np.asarray(data_max), num_of_bins)
xb_gen, pb_gen, pberr_gen = getBinnedDistribution(
np.asarray(sorted_len), np.asarray(career_max), num_of_bins)
ax.errorbar((xb_data[1:] + xb_data[:-1]) / 2,
pb_data,
yerr=pberr_data,
fmt='o-',
color='grey',
label='data',
alpha=0.9)
ax.errorbar((xb_gen[1:] + xb_gen[:-1]) / 2,
pb_gen,
yerr=pberr_gen,
fmt='-',
color='r',
label='R-model',
alpha=0.9)
else:
ax.set_xscale('log')
ax.set_yscale('log')
xb_data, pb_data, pberr_data = getLogBinnedDistribution(
np.asarray(career_len), np.asarray(data_max), num_of_bins)
xb_gen, pb_gen, pberr_gen = getLogBinnedDistribution(
np.asarray(sorted_len), np.asarray(career_max), num_of_bins)
ax.errorbar(xb_data,
pb_data,
yerr=pberr_data,
fmt='o-',
color='grey',
label='data',
alpha=0.9)
ax.errorbar(xb_gen,
pb_gen,
yerr=pberr_gen,
fmt='-',
color='r',
label='R-model',
alpha=0.9)
def get_imapct_distr():
''' ---------------------------------------------- '''
''' MOVIE YO '''
professions = [('director', 'k'), ('producer', 'b'), ('writer', 'r'),
('composer', 'g'), ('art-director', 'y')]
num_of_bins = 20
title_font = 25
seaborn.set_style('white')
f, ax = plt.subplots(2, 3, figsize=(25, 15))
st = f.suptitle("IMDb normalized impact distributions",
fontsize=title_font)
FOLDER = 'ProcessedDataNormalized'
for (label, color) in professions:
num_car = str(
int(
round(
len(
os.listdir('Data/Film/film-' + label +
'-simple-careers')) / 1000.0))) + 'k'
file_avg = FOLDER + '/1_impact_distributions/film_average_ratings_dist_' + label + '.dat'
file_cnt = FOLDER + '/1_impact_distributions/film_rating_counts_dist_' + label + '.dat'
file_mets = FOLDER + '/1_impact_distributions/film_metascores_dist_' + label + '.dat'
file_crit = FOLDER + '/1_impact_distributions/film_critic_review_dist_' + label + '.dat'
file_user = FOLDER + '/1_impact_distributions/film_user_review_dist_' + label + '.dat'
average_ratings = np.asarray(
[round(float(line.strip()), 2) for line in open(file_avg)])
rating_counts = [
round(float(line.strip()), 2) for line in open(file_cnt)
]
metascores = [
round(float(line.strip()), 1) for line in open(file_mets)
]
critic_review = [
round(float(line.strip()), 2) for line in open(file_crit)
]
user_review = [
round(float(line.strip()), 2) for line in open(file_user)
]
# plot avg ratings
x_average_ratings, p_average_ratings = getDistribution(
average_ratings, True)
bx_average_ratings, bp_average_ratings, bperr_average_ratings = getBinnedDistribution(
x_average_ratings, p_average_ratings, num_of_bins)
ax[0, 0].set_title('IMDb - average rating', fontsize=20)
ax[0, 0].plot(x_average_ratings,
p_average_ratings,
color,
marker='o',
alpha=0.1,
linewidth=0,
label=label + ', ' + str(num_car))
ax[0, 0].errorbar(
(bx_average_ratings[1:] + bx_average_ratings[:-1]) / 2,
bp_average_ratings,
yerr=bperr_average_ratings,
fmt=color + '-',
linewidth=2)
# plot rating counts
x_rating_counts, p_rating_counts = getDistribution(rating_counts, True)
bx_rating_counts, bp_rating_counts, bperr_rating_counts = getBinnedDistribution(
x_rating_counts, p_rating_counts, num_of_bins)
ax[0, 1].set_title('IMDb - rating count', fontsize=20)
ax[0, 1].set_xscale('log')
ax[0, 1].set_yscale('log')
ax[0, 1].plot(x_rating_counts,
p_rating_counts,
color + 'o',
alpha=0.8,
label=label) # + ', ' + str(num_wr))
#ax[0,1].errorbar((bx_rating_counts[1:] + bx_rating_counts[:-1])/2, bp_rating_counts, yerr=bperr_rating_counts, fmt='b-', linewidth = 2)
# plot metascores
x_metascores, p_metascores = getDistribution(metascores, True)
bx_metascores, bp_metascores, bperr_metascores = getBinnedDistribution(
x_metascores, p_metascores, num_of_bins)
ax[0, 2].set_title('IMDb - metascores', fontsize=20)
ax[0, 2].plot(x_metascores,
p_metascores,
color + 'o',
alpha=0.2,
label=label) # + ', ' + str(len(metascores)))
ax[0, 2].errorbar((bx_metascores[1:] + bx_metascores[:-1]) / 2,
bp_metascores,
yerr=bperr_metascores,
fmt=color + '-',
linewidth=2)
# plot critic review count
x_critic_review, p_critic_review = getDistribution(critic_review, True)
ax[1, 0].set_title('IMDb - critic_review', fontsize=20)
ax[1, 0].set_xscale('log')
ax[1, 0].set_yscale('log')
ax[1, 0].plot(x_critic_review,
p_critic_review,
color + 'o',
alpha=0.8,
label=label) #+ ', ' + str(len(critic_review)))
# plot user review count
x_user_review, p_user_review = getDistribution(user_review, True)
ax[1, 1].set_title('IMDb - user_review', fontsize=20)
ax[1, 1].set_xscale('log')
ax[1, 1].set_yscale('log')
ax[1, 1].plot(x_user_review,
p_user_review,
color + 'o',
alpha=0.8,
label=label) # + ', ' + str(len(user_review)))
''' ---------------------------------------------- '''
''' MOVIE YO '''
genres = [('electro', 'k'), ('pop', 'b')]
for (genre, color) in genres:
num_mus = str(
int(
round(
len(
os.listdir('Data/Music/music-' + genre +
'-simple-careers')) / 1000.0))) + 'k'
file_music = FOLDER + '/1_impact_distributions/music_rating_counts_dist_' + genre + '.dat'
average_ratings = np.asarray(
[round(float(line.strip())) for line in open(file_music)])
x_rating_counts, p_rating_counts = getDistribution(
average_ratings, True)
print len(average_ratings)
ax[1, 2].set_title('Music - playcount', fontsize=20)
ax[1, 2].set_xscale('log')
ax[1, 2].set_yscale('log')
ax[1, 2].plot(x_rating_counts,
p_rating_counts,
color + 'o',
alpha=0.2,
label=genre + ', ' + num_mus)
align_plot(ax)
plt.savefig('impact_distributions_normalized.png')
plt.close()
def get_impact_correlations():
num_of_bins = 12
title_font = 25
seaborn.set_style('white')
professions = [('director', 'royalblue'), ('producer', 'b'),
('writer', 'r'), ('composer', 'g'), ('art-director', 'y')]
for mode in ['', 'Normalized']:
f, ax = plt.subplots(2, 3, figsize=(25, 15))
st = f.suptitle("IMDb impact correlations - " + mode,
fontsize=title_font)
for (label, color) in professions[0:1]:
impacts = zip(*[[
float(aaa) if 'tt' not in aaa else aaa
for aaa in line.strip().split('\t')
] for line in open('ProcessedData' + mode +
'/7_multiple_impacts/film_multiple_impacts_' +
label + '.dat')])
Alpha = 0.05
ax[0, 0].set_ylabel('avg rating', fontsize=20)
ax[0, 0].set_xlabel('rating cnt', fontsize=20)
ax[0, 0].set_xscale('log')
avg, cnt = get_rid_of_zeros(impacts[2], impacts[1])
ax[0, 0].plot(impacts[2],
impacts[1],
'o',
color=color,
alpha=Alpha,
label=label)
xb_avg, pb_avg, pberr_avg = getLogBinnedDistribution(
np.asarray(avg), np.asarray(cnt), num_of_bins)
ax[0, 0].errorbar(xb_avg,
pb_avg,
yerr=pberr_avg,
fmt='^-',
color='r')
x_cnt_meta, p_cnt_meta, perr_cnt_meta = getBinnedDistribution(
np.asarray(impacts[3]), np.asarray(impacts[1]), num_of_bins)
meta, avg = get_rid_of_zeros(impacts[3], impacts[1])
ax[0, 1].set_xlabel('metascore', fontsize=20)
ax[0, 1].plot(meta,
avg,
'o',
color=color,
alpha=Alpha,
label=label)
ax[0, 1].errorbar(
(x_cnt_meta[1:] + x_cnt_meta[:-1]) / 2,
p_cnt_meta,
yerr=perr_cnt_meta,
fmt='^-',
color='r',
label='$corr=$' + str(
round(
stats.pearsonr((x_cnt_meta[1:] + x_cnt_meta[:-1]) / 2,
p_cnt_meta)[0],
4))) #, alpha = Alpha, label = label)
ax[0, 2].set_ylabel('#critic review', fontsize=20)
ax[0, 2].set_xlabel('#user review', fontsize=20)
ax[0, 2].set_xscale('log')
ax[0, 2].set_yscale('log')
crit, user = get_rid_of_zeros(impacts[4], impacts[5])
xb_crit, pb_crit, pberr_crit = getLogBinnedDistribution(
np.asarray(crit), np.asarray(user), num_of_bins)
ax[0, 2].plot(crit,
user,
'o',
color=color,
alpha=Alpha,
label=label)
ax[0, 2].errorbar(xb_crit,
pb_crit,
yerr=pberr_crit,
fmt='^-',
color='r')
#ax[1,0].xaxis.get_major_formatter().set_powerlimits((0, 1))
ax[1, 0].set_xscale('log')
cnttt, metatt = get_rid_of_zeros(impacts[2], impacts[3])
x_cnt_metat, p_cnt_metat, perr_cnt_metat = getLogBinnedDistribution(
np.asarray(cnttt), np.asarray(metatt), num_of_bins)
ax[1, 0].set_xlabel('rating cnt', fontsize=20)
ax[1, 0].set_ylabel('metascore', fontsize=20)
ax[1, 0].plot(cnttt,
metatt,
'o',
color=color,
alpha=Alpha,
label=label)
ax[1, 0].errorbar(x_cnt_metat,
p_cnt_metat,
yerr=perr_cnt_metat,
fmt='^-',
color='r') #, alpha = Alpha, label = label)
ax[1, 1].set_xlabel('rating cnt', fontsize=20)
ax[1, 1].set_ylabel('#critic review', fontsize=20)
cnt, crit = get_rid_of_zeros(impacts[2], impacts[4])
xb_cnt_crit, pb_cnt_crit, pberr_cnt_crit = getLogBinnedDistribution(
np.asarray(cnt), np.asarray(crit), num_of_bins)
ax[1, 1].loglog(impacts[2],
impacts[4],
'o',
color=color,
alpha=Alpha,
label=label)
ax[1, 1].errorbar(xb_cnt_crit,
pb_cnt_crit,
yerr=pberr_cnt_crit,
fmt='^-',
color='r')
ax[1, 2].set_xlabel('rating cnt', fontsize=20)
ax[1, 2].set_ylabel('#user review', fontsize=20)
cnt, user = get_rid_of_zeros(impacts[2], impacts[5])
xb_cnt_crit, pb_cnt_user, pberr_cnt_user = getLogBinnedDistribution(
np.asarray(cnt), np.asarray(user), num_of_bins)
ax[1, 2].loglog(impacts[2],
impacts[5],
'o',
color=color,
alpha=Alpha,
label=label)
ax[1, 2].errorbar(xb_cnt_crit,
pb_cnt_user,
yerr=pberr_cnt_user,
fmt='^-',
color='r')
align_plot(ax)
plt.savefig('correlations_' + mode + '.png')
plt.close()
def get_length_plots():
title_font = 25
num_of_bins = 20
seaborn.set_style('white')
f, ax = plt.subplots(2, 3, figsize=(22, 15))
#st = f.suptitle("IMDb Inflation of impact measures", fontsize=title_font)
file_avg_year = 'ProcessedData/3_inflation_curves/film_yearly_average_ratings_dist_director.dat'
average_ratings_year = np.asarray(
[line.strip() for line in open(file_avg_year)])
x_average_ratings_year, y_average_ratings_year = get_num_per_year(
average_ratings_year)
#ax[0,0].plot(x_average_ratings_year, y_average_ratings_year, 'ko', label = 'movies', alpha = 0.8)
#ax[0,0].set_title('#movies', fontsize = title_font)
ax[0, 0].set_yscale('log')
ax[0, 0].plot(x_average_ratings_year,
y_average_ratings_year,
'ko',
label='movies',
alpha=0.6)
ax[0, 0].set_title('#movies', fontsize=title_font)
file_avg_year_electro = 'ProcessedData/3_inflation_curves/music_yearly_rating_counts_dist_electro.dat'
file_avg_year_pop = 'ProcessedData/3_inflation_curves/music_yearly_rating_counts_dist_pop.dat'
average_ratings_year_electro = np.asarray(
[line.strip() for line in open(file_avg_year_electro)])
average_ratings_year_pop = np.asarray(
[line.strip() for line in open(file_avg_year_pop)])
x_average_ratings_year_electro, y_average_ratings_year_electro = get_num_per_year(
average_ratings_year_electro)
x_average_ratings_year_pop, y_average_ratings_year_pop = get_num_per_year(
average_ratings_year_pop)
xb_average_ratings_year_electro, pb_average_ratings_year_electro, pberr_average_ratings_year_electro = getBinnedDistribution(
x_average_ratings_year_electro, y_average_ratings_year_electro,
num_of_bins)
ax[0, 1].set_yscale('log')
ax[0, 1].plot(x_average_ratings_year_electro,
y_average_ratings_year_electro,
'ko',
label='electro',
alpha=0.6)
ax[0, 1].plot(x_average_ratings_year_pop,
y_average_ratings_year_pop,
'bo',
label='pop',
alpha=0.6)
ax[0, 1].set_title('#tracks', fontsize=title_font)
ax[0, 2].set_title('#books', fontsize=title_font)
align_plot(ax)
plt.savefig('num_of_products_length_data.png')