def exp11():
"""
Show correlation for each feature
"""
poems = getPoemModel().poems
scores = {}
scores["affect"] = getAffectRatios()
scores["cLength"] = getLogAverageCommentLength()
scores["rating"] = getPoemScores()
scores["typeToken"] = getCommentTypeTokenRatio(100)
scores["numC"] = getNumberOfComments(True) # use log
result = {}
for k1, v1 in scores.items():
for feature in poems.values()[0].keys():
cor, p = getCorrelation(poems, v1, feature)
if result.get(feature, None) is None:
result[feature] = {k1: (cor, p)}
else:
result[feature][k1] = (cor, p)
for k1 in sorted(result.keys(), key=lambda x: result[x]["affect"][1]): # sort by affect
print "\\\\", k1, "& %0.2f & %0.4f" % result[k1]["affect"], "& %0.2f & %0.4f" % result[k1][
"typeToken"
], "& %0.2f & %0.4f" % result[k1]["cLength"], "& %0.2f & %0.4f" % result[k1][
"rating"
], "& %0.2f & %0.4f" % result[
k1
][
"numC"
]
def exp06():
"""
Can we predict the log of the number of responses? Not much better.
"""
m = getPoemModel()
poems = m.poems
scores = getNumberOfComments(True) # use log
makePlots(poems, scores, "log of number of comments", "../experiments/exp06.pdf")
runPredictCV(poems, scores, DEFAULT_FEATURE_LIST)
def exp05():
"""
Can we predict the number of responses? Not so well.
"""
m = getPoemModel()
poems = m.poems
scores = getNumberOfComments()
makePlots(poems, scores, "number of comments", "../experiments/exp05.pdf")
runPredictCV(poems, scores, DEFAULT_FEATURE_LIST)
