def plotCondSecond(df, num, color, first):
df_cond = df[df["minDist"] == num]
return plotBar(
df_cond,
"secondMinDist",
"rating",
range(7)[num:],
color=color,
x_label="Reviewer Distance to Second Closest Author",
y_label="Avg Rating",
sameFigure=(not first),
plotMean=False
)
df.loc[df["authorCountryMode"] == "United Kingdom", "authorCountryMode"]\
= "United\nKingdom"
countryCounts = df['authorCountryMode'].value_counts().to_dict()
countries = [c for c, count in countryCounts.iteritems() if count > 10]
countries.sort(key=lambda c: df[df['authorCountryMode']==c]['accepted'].mean())
countries = countries[1:]
p = plotBar(
df,
"authorCountryMode",
"accepted",
countries,
title="Proportion of Papers Accepted by Country",
x_label="Mode Author Country",
y_label="Proportion Accepted",
categorical=True,
errorBars=True
)
j = 0
for container in plt.gca().containers:
for i, child in enumerate(container.get_children()):
if j > 3:
child.set_color(plt.cm.coolwarm_r((child.get_height() - 0.05)/0.20))
j += 1
gcf().set_size_inches((40, 10))
y = ylim()[1] - 0.025
for a in paper.authors:
authorExpList.append(a.topPastPapers)
numRuns = 500
avgRatings = []
errors = []
for i in range(1, max(numAuthorsList) + 1):
ratings = np.empty([numRuns, 1])
for j in range(numRuns):
sample = random.sample(authorExpList, i)
maxExp = max(sample)
ratings[j] = getAvg(maxExp)
avgRatings.append(ratings.mean())
errors.append(ratings.std()/math.sqrt(ratings.shape[0]))
p1 = plotBar(
df,
"numAuthors",
"avgRating",
range(1, 8),
color="green",
x_label="Number of Authors",
y_label="Average Rating",
marker="o",
plotMean=False,
)
p2 = plt.errorbar(np.arange(1, 8), avgRatings[:7], yerr=errors[:7], marker = 'o')
plt.xlim([0,8])
plt.legend((p1, p2), ('Real', 'Simulated'), loc=4)
plt.show()
x_percentile=False,
xlim=[-.1, .1])
df_dist = df[df["distDiff"] >= 0]
plotBucket(df,
"distDiff",
"higherRating",
delta=5,
x_label="Difference in Min Distance to Reviewer",
y_label="Probability of a Higher Rating",
color="Green",
x_percentile=False)
plotBar(df_original,
"minDist",
"paperRatingDiff", [1, 2, 3, 4, 5, 6, 7, 8],
x_label="Min Distance between Reviewer and Paper Authors",
y_label="Deviation from Paper Average Rating",
title="Deviation from Paper Average vs. Min Dist to Reviewer",
color="Blue")
# df["avgRatingDist"] = df["rating"] - df["rating2"]
# for i in range(7):
# for j in range(7):
# if (j >= i):
# print "(%d, %d)" % (i,j)
# print df[(df["minDist"] == i) & (df["minDist2"]==j)]["avgRatingDist"].mean()
# print df[(df["minDist"] == i) & (df["minDist2"]==j)]["avgRatingDist"].shape[0]
show()
plotBucket(
df,
"paperId",
"accepted",
x_label="Submission Order",
y_label="P(Accept)",
title="Acceptance vs. Submission Order",
numBuckets=10
)
#how subsequent reviews influence each other
plotBar(
df_review,
"order",
"rating",
range(12)[1:],
x_label="Review Order",
y_label="Rating",
title="Rating vs. Order of Review",
)
df = df_review
plots = []
colors =\
["red", "pink", "", "cyan", "blue",]
for i in [-2, -1, 1, 2]:
df["rating%d" % i] = df["rating"] == i
plots.append(plotBar(
df_review,
"avgRating",
color="white",
x_label="Number of Authors",
y_label="Average Rating",
marker="None",
x_percentile=False)
p = []
df1 = df.copy()[slices[0]]
ofInterest = df1["numAuthors"] >= 3
newValue = np.round(df1[ofInterest]["numAuthors"].mean(), 2)
df1.loc[ofInterest, "numAuthors"] = newValue
p.append(
plotBar(df1,
"numAuthors",
"avgRating", [1, 2, newValue],
color="blue",
sameFigure=True,
marker="s",
plotMean=False))
colors = ["red", "green", "purple"]
p.extend([
plotBucket(df[slices[i]],
"numAuthors",
"avgRating",
numBuckets=4,
color=colors[i - 1],
sameFigure=True,
marker="s",
plotMean=False) for i in [1, 2, 3]
])
plotBucket(df,
"paperId",
"accepted",
x_label="Submission Order",
y_label="P(Accept)",
title="Acceptance vs. Submission Order",
numBuckets=10)
#how subsequent reviews influence each other
plotBar(
df_review,
"order",
"rating",
range(12)[1:],
x_label="Review Order",
y_label="Rating",
title="Rating vs. Order of Review",
)
df = df_review
plots = []
colors =\
["red", "pink", "", "cyan", "blue",]
for i in [-2, -1, 1, 2]:
df["rating%d" % i] = df["rating"] == i
plots.append(
plotBar(df_review,
plotBucket(
df,
"distDiff",
"higherRating",
delta=5,
x_label="Difference in Min Distance to Reviewer",
y_label="Probability of a Higher Rating",
color="Green",
x_percentile=False,
)
plotBar(
df_original,
"minDist",
"paperRatingDiff",
[1, 2, 3, 4, 5, 6, 7, 8],
x_label="Min Distance between Reviewer and Paper Authors",
y_label="Deviation from Paper Average Rating",
title="Deviation from Paper Average vs. Min Dist to Reviewer",
color="Blue",
)
# df["avgRatingDist"] = df["rating"] - df["rating2"]
# for i in range(7):
# for j in range(7):
# if (j >= i):
# print "(%d, %d)" % (i,j)
# print df[(df["minDist"] == i) & (df["minDist2"]==j)]["avgRatingDist"].mean()
# print df[(df["minDist"] == i) & (df["minDist2"]==j)]["avgRatingDist"].shape[0]
#Plot co-author dist
p1 = plotBucket(
df_merged,
"avgDist",
"rating",
delta=10,
x_label="Reviewer Author Distance",
y_label="Avg Rating",
xlim=[0, 8],
x_percentile=False
)
p2 = plotBar(
df_merged,
"minDist",
"rating",
range(7)[1:],
color="red",
sameFigure=True,
)
legend([p1, p2],
["Average Author Distance",
"Min Author Distances"])
#Plot min co-author dist vs P(Accept)
g = df_merged.groupby('paperId')
h = pd.concat([
g["minDist"].mean(),
g["minDist"].min(),
g["accepted"].median()], axis=1)
color="white",
x_label="Number of Authors",
y_label="Average Rating",
marker="None",
x_percentile=False
)
p = []
df1 = df.copy()[slices[0]]
ofInterest = df1["numAuthors"] >= 3
newValue = np.round(df1[ofInterest]["numAuthors"].mean(), 2)
df1.loc[ofInterest, "numAuthors"] = newValue
p.append(plotBar(
df1,
"numAuthors",
"avgRating",
[1, 2, newValue],
color="blue",
sameFigure=True,
marker="s",
plotMean=False))
colors = ["red", "green", "purple"]
p.extend([
plotBucket(
df[slices[i]],
"numAuthors",
"avgRating",
numBuckets=4,
color=colors[i-1],
sameFigure=True,
marker="s",
df.loc[df["authorCountryMode"] == "United Kingdom", "authorCountryMode"]\
= "United\nKingdom"
countryCounts = df['authorCountryMode'].value_counts().to_dict()
countries = [c for c, count in countryCounts.iteritems() if count > 10]
countries.sort(
key=lambda c: df[df['authorCountryMode'] == c]['accepted'].mean())
countries = countries[1:]
p = plotBar(df,
"authorCountryMode",
"accepted",
countries,
title="Proportion of Papers Accepted by Country",
x_label="Mode Author Country",
y_label="Proportion Accepted",
categorical=True,
errorBars=True)
j = 0
for container in plt.gca().containers:
for i, child in enumerate(container.get_children()):
if j > 3:
child.set_color(
plt.cm.coolwarm_r((child.get_height() - 0.05) / 0.20))
j += 1
gcf().set_size_inches((40, 10))
y = ylim()[1] - 0.025
delta=10,
color="white",
x_label="Number of Authors",
y_label="Average Rating",
marker="None",
x_percentile=False)
df1 = df_paper.copy()[slices[0]]
ofInterest = df1["#Authors"] >= 3
newValue = np.round(df1[ofInterest]["#Authors"].mean(), 2)
df1.loc[ofInterest, "#Authors"] = newValue
p1 = plotBar(
df1,
"#Authors",
"avgRating",
[1, 2, newValue],
color="blue",
sameFigure=True,
marker="s",
plotMean=False)
p2 = plotBucket(
df_paper[slices[1]],
"#Authors",
"avgRating",
delta=20,
color="red",
sameFigure=True,
x_percentile=False,
marker="s",
plotMean=False)
# ycol,
# delta=5,
# color="blue",
# title="default",
# x_label="default",
# y_label="default",
# x_percentile=True,
# xlim=None):
authorFrame = userFrame[userFrame["#Papers"] > 0]
authorFrame["acceptanceRate"] = authorFrame["#Accepted"] \
* 1.0/authorFrame["#Papers"]
plotBar(authorFrame,
"#Papers",
"acceptanceRate", [0, 1, 2, 3, 4, 5],
title="Acceptance Rate vs. Number of Submissions",
x_label="Number of Submissions",
y_label="Acceptance Rate",
xlim=[0, 6])
plotBucket(userFrame,
"#PastPapers",
"#Papers",
x_label="Number of Past Papers",
y_label="Number of Submissions",
x_percentile=False,
xlim=[0, 200])
plotBucket(authorFrame,
"#PastPapers",
"acceptanceRate",
# delta=5,
# color="blue",
# title="default",
# x_label="default",
# y_label="default",
# x_percentile=True,
# xlim=None):
authorFrame = userFrame[userFrame["#Papers"] > 0]
authorFrame["acceptanceRate"] = authorFrame["#Accepted"] \
* 1.0/authorFrame["#Papers"]
plotBar(
authorFrame,
"#Papers",
"acceptanceRate",
[0, 1, 2, 3, 4, 5],
title="Acceptance Rate vs. Number of Submissions",
x_label="Number of Submissions",
y_label="Acceptance Rate",
xlim=[0, 6]
)
plotBucket(
userFrame,
"#PastPapers",
"#Papers",
x_label="Number of Past Papers",
y_label="Number of Submissions",
x_percentile=False,
xlim=[0, 200])