def f3():
df = df_paper
plotBucket(df,
"paperId",
"accepted",
x_label="Submission Order",
y_label="P(Accept)",
title="Acceptance vs. Submission Order",
numBuckets=10)
def f3(): df = df_paper plotBucket( df, "paperId", "accepted", x_label="Submission Order", y_label="P(Accept)", title="Acceptance vs. Submission Order", numBuckets=10 )
def f2():
df = pd.merge(df_review.groupby("userId")["rating"].std().reset_index(),
df_reviewer,
on="userId")
df["var"] = df["rating"]**2
plotBucket(
df,
"dateFirstPaper",
"var",
x_label="Date of First Paper",
y_label="Variance of Ratings",
x_percentile=False,
title="Rating Variance vs. Reviewer Seniority",
numBuckets=5,
)
def f2():
df = pd.merge(
df_review.groupby("userId")["rating"].std().reset_index(),
df_reviewer,
on="userId")
df["var"] = df["rating"] ** 2
plotBucket(
df,
"dateFirstPaper",
"var",
x_label="Date of First Paper",
y_label="Variance of Ratings",
x_percentile=False,
title="Rating Variance vs. Reviewer Seniority",
numBuckets=5,
)
def f1():
df = pd.merge(
df_review.groupby("userId")["reviewLength"].mean().reset_index(),
df_reviewer,
on="userId")
plotBucket(df,
"numBids",
"reviewLength",
x_label="Number of Bids",
y_label="Average Review Length",
x_percentile=False,
title="Review Quality vs. Number of Bids",
numBuckets=7,
xlim=[0, 100])
plotFrequencyHistogram(df,
'numBids',
'Number of Bids',
myBins=[0, 5, 10, 15, 20, 25, 30, 35, 40, 45, 50])
def f1():
df = pd.merge(
df_review.groupby("userId")["reviewLength"].mean().reset_index(),
df_reviewer,
on="userId")
plotBucket(
df,
"numBids",
"reviewLength",
x_label="Number of Bids",
y_label="Average Review Length",
x_percentile=False,
title="Review Quality vs. Number of Bids",
numBuckets=7,
xlim=[0,100]
)
plotFrequencyHistogram(
df,
'numBids',
'Number of Bids',
myBins=[0,5,10,15,20,25,30, 35, 40, 45, 50]
)
from pylab import *
with warnings.catch_warnings():
warnings.simplefilter("ignore")
import pandas as pd
from utilities.plotBucket import plotBucket
from utilities.plotBucket import plotBar
df_rating = pd.read_pickle(
"savedFrames/ratingPrediction/ratingTable")
df_paper = pd.read_pickle(
"savedFrames/summaryStatistics/papersTable")
p1 = plotBucket(
df_rating,
"authorsMaxPastPaper",
"rating",
color="blue",
x_label="Number of Past Papers",
y_label="Average Rating")
setp(p1, linewidth=1.5)
p2 = plotBucket(
df_rating,
"primaryAuthorPastPaperCount",
"rating",
color="red",
sameFigure=True,
marker="s")
setp(p2, linewidth=1.5)
legend([p1, p2], ["Most Experienced Author", "Primary Author"], loc=4)
df = pd.merge(df, df_mostSimilar, on=['paperId'])
df = pd.merge(df,
papersFrame[["paperId",
"maxConnectivity",
"maxPageRank",
"maxEigenCenter",
"maxDegCenter",
"primarySpecificSubjectArea",
"primarySubjectArea"]],
on=["paperId"])
#Average Rating vs. Number of Past Papers
p1 = plotBucket(
df_rating,
"authorsMaxPastPaper",
"rating",
delta=10,
color="blue",
x_label="Number of Past Papers",
y_label="Average Rating")
setp(p1, linewidth=1.5)
p2 = plotBucket(
df_rating,
"primaryAuthorPastPaperCount",
"rating",
delta=10,
color="red",
sameFigure=True,
marker="s")
setp(p2, linewidth=1.5)
legend([p1, p2], ["Most Experienced Author", "Primary Author"], loc=4)
fig = plt.figure()
fig.set_facecolor("white")
p = plt.errorbar(range(1, 8),
meansAvg,
marker="o",
color="red",
yerr=stdErrorsAvg)
plt.xlim([0, 8])
plt.ylabel('Avg Rating of Paper')
plt.xlabel('Avg Distance between Reviewer and Paper Authors')
fig.suptitle('Avg Rating Given Avg Distance')
plotBucket(reviewFrame,
"avgDist",
"rating",
delta=10,
y_label="Avg Rating of Paper",
x_label="Avg Distance between Reviewer and Paper Authors",
color="red",
x_percentile=False)
# plt.figure(22)
# plt.scatter(reviewsWithHistory['numPastPapers'], reviewsWithHistory['rating'] + np.random.normal(loc=0, scale=0.2, size=2971),
# c = ['red' if a else 'blue' for a in reviewsWithHistory['accepted']])
meansPaper = []
stdDevsPaper = []
numsPaper = []
stdErrorsPaper = []
bins = [0, 5, 10, 20, 40, 80, 160, 320, 640]
for i in range(len(bins) - 1):
meansPaper.append(reviewsWithHistory[
df_paper = pd.read_pickle("savedFrames/iteration5/paperTable")
df_review = pd.read_pickle("savedFrames/iteration5/reviewTable")
df_industry = pd.read_pickle("savedFrames/iteration5/industryReviewTable")
df_author = pd.read_pickle("savedFrames/iteration5/authorTable")
#SECTION 1
#PAST PAPER COUNTS
df = df_paper # [df_paper["paperCountPrimary"] > 0]
primary_different =\
(df["paperCountPrimary"] != df["paperCountMax"])\
| (df["paperCountMax"] == df["paperCount2ndHighest"])
df = df_paper
plotBucket(df,
"paperCountAvg",
"avgRating",
numBuckets=5,
color="green",
x_label="Number of Past Papers",
y_label="Average Rating",
title="Rating vs. Average Past Paper Counts of Authors")
ylim([-1.8, 0])
p1 = plotBucket(df,
"topPaperCountAvg",
"avgRating",
numBuckets=6,
color="green",
x_label="Number of Past Papers",
y_label="Average Rating",
title="Rating vs. Average Past Paper Counts of Authors")
p2 = plotBucket(df,
"paperCountAvg",
"avgRating",
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",
x_label="Number of Past Papers",
y_label="Acceptance Rate",
x_percentile=False,
color="Red",
xlim=[0, 200])
plotBucket(papersFrame,
"authorsMaxPastPaper",
"savedFrames/iteration5/industryReviewTable")
df_author = pd.read_pickle(
"savedFrames/iteration5/authorTable")
#SECTION 1
#PAST PAPER COUNTS
df = df_paper # [df_paper["paperCountPrimary"] > 0]
primary_different =\
(df["paperCountPrimary"] != df["paperCountMax"])\
| (df["paperCountMax"] == df["paperCount2ndHighest"])
df = df_paper
plotBucket(
df,
"paperCountAvg",
"avgRating",
numBuckets=5,
color="green",
x_label="Number of Past Papers",
y_label="Average Rating",
title="Rating vs. Average Past Paper Counts of Authors")
ylim([-1.8, 0])
p1 = plotBucket(
df,
"topPaperCountAvg",
"avgRating",
numBuckets=6,
color="green",
x_label="Number of Past Papers",
y_label="Average Rating",
title="Rating vs. Average Past Paper Counts of Authors")
p2 = plotBucket(
def plotTest(df, col, col2):
plotBucket(
df,
col,
col2)
"paperId", "userId2", "rating2", "authorReviewerSimilarity2",
"pastPaperSimilarity2", "maxAuthorReviewerSimilarity2", "minDist2"
]
df = pd.merge(df, df2, on='paperId')
df = df[(df["userId"] != df["userId2"]) & (df["rating"] != df["rating2"])]
df["simDiff"] = df["authorReviewerSimilarity"] - df["authorReviewerSimilarity2"]
df["distDiff"] = df["minDist"] - df["minDist2"]
df["higherRating"] = df["rating"] > df["rating2"]
plotBucket(df,
"simDiff",
"higherRating",
x_label="Difference in Author/Reviewer Similarity",
y_label="Probability of a Higher Rating",
delta=10,
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,
import warnings
from pylab import *
with warnings.catch_warnings():
warnings.simplefilter("ignore")
import pandas as pd
from utilities.plotBucket import plotBucket
from utilities.plotBucket import plotBar
df_rating = pd.read_pickle("savedFrames/ratingPrediction/ratingTable")
df_paper = pd.read_pickle("savedFrames/summaryStatistics/papersTable")
p1 = plotBucket(df_rating,
"authorsMaxPastPaper",
"rating",
color="blue",
x_label="Number of Past Papers",
y_label="Average Rating")
setp(p1, linewidth=1.5)
p2 = plotBucket(df_rating,
"primaryAuthorPastPaperCount",
"rating",
color="red",
sameFigure=True,
marker="s")
setp(p2, linewidth=1.5)
legend([p1, p2], ["Most Experienced Author", "Primary Author"], loc=4)
p1 = plotBucket(df_paper,
"authorsMaxPastPaper",
"accepted",
"minDist2",
]
df = pd.merge(df, df2, on="paperId")
df = df[(df["userId"] != df["userId2"]) & (df["rating"] != df["rating2"])]
df["simDiff"] = df["authorReviewerSimilarity"] - df["authorReviewerSimilarity2"]
df["distDiff"] = df["minDist"] - df["minDist2"]
df["higherRating"] = df["rating"] > df["rating2"]
plotBucket(
df,
"simDiff",
"higherRating",
x_label="Difference in Author/Reviewer Similarity",
y_label="Probability of a Higher Rating",
delta=10,
x_percentile=False,
xlim=[-0.1, 0.1],
)
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,
df_paper = pd.read_pickle(
"savedFrames/summaryStatistics/papersTable")
df_dist = pd.read_pickle(
"savedFrames/reviewStatistics/reviewTable")
userFrame = pd.read_pickle(
"savedFrames/summaryStatistics/userTable")
df_mostSimilar = pd.read_pickle(
"savedFrames/ratingPrediction/mostSimilarTable")
df_merged = pd.merge(df_rating, df_dist, on=['paperId', 'userId', 'rating'])
df_merged = pd.merge(df_merged, df_mostSimilar, on=['paperId'])
#Plot past paper count vs. average rating
p1 = plotBucket(
df_rating,
"authorsMaxPastPaper",
"rating",
color="blue",
x_label="Number of Past Papers",
y_label="Average Rating")
setp(p1, linewidth=1.5)
p2 = plotBucket(
df_rating,
"primaryAuthorPastPaperCount",
"rating",
color="red",
sameFigure=True,
marker="s")
setp(p2, linewidth=1.5)
legend([p1, p2], ["Most Experienced Author", "Primary Author"], loc=4)
maxSimCol = "maxAuthorReviewerSimilarity"
def plotTest(df, col, col2):
plotBucket(
df,
col,
col2)
p = plotBucket(
df,
maxSimCol,
"rating",
x_label="Similarity",
y_label="Rating",
delta=15,
title=
"Average Rating vs. Similarity of Reviewer to Most Experienced Author",
marker="s",
color="green",
xlim=[0, 100]
)
setp(p, linewidth=2, alpha=1)
p = plotBucket(
df,
"authorReviewerSimilarity",
"rating",
x_label="Similarity",
y_label="Rating",
delta=15,
" Review Submission\n Deadline",
va="top",
color="gray",
alpha=.8)
labels_month = ['3/20', '3/30', '4/10', '4/20', '4/30']
dates_month = transformDates(labels_month)
#Plot 3 -- Submission Time vs. Rating
plotBucket(
df,
'time',
'rating',
numBuckets=5,
x_percentile=False,
title='Rating v. Submission Date',
x_label="Submission Date",
y_label="Average Review Rating",
plotMean=False,
)
plotBucket(
df_more,
'time',
'rating',
numBuckets=5,
x_percentile=False,
title='Rating v. Submission Date',
x_label="Submission Date",
y_label="Average Review Rating",
color="red",
)
stdErrorsAvg.append(stdDevsAvg[-1] / math.sqrt(numsAvg[-1]))
fig = plt.figure()
fig.set_facecolor("white")
p = plt.errorbar(range(1, 8), meansAvg, marker="o", color="red", yerr=stdErrorsAvg)
plt.xlim([0, 8])
plt.ylabel("Avg Rating of Paper")
plt.xlabel("Avg Distance between Reviewer and Paper Authors")
fig.suptitle("Avg Rating Given Avg Distance")
plotBucket(
reviewFrame,
"avgDist",
"rating",
delta=10,
y_label="Avg Rating of Paper",
x_label="Avg Distance between Reviewer and Paper Authors",
color="red",
x_percentile=False,
)
# plt.figure(22)
# plt.scatter(reviewsWithHistory['numPastPapers'], reviewsWithHistory['rating'] + np.random.normal(loc=0, scale=0.2, size=2971),
# c = ['red' if a else 'blue' for a in reviewsWithHistory['accepted']])
meansPaper = []
stdDevsPaper = []
numsPaper = []
stdErrorsPaper = []
bins = [0, 5, 10, 20, 40, 80, 160, 320, 640]
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",
x_label="Number of Past Papers",
y_label="Acceptance Rate",
x_percentile=False,
color="Red",
xlim=[0, 200])