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 exp03():
"""
We can predict log of average comment length with 10% reduction in error
over baseline (better than average comment length), but this is still worse
than predicting the affect ratio. Why? Is there another descriptive feature
of the comments that we can better describe?
Are the comments with different affect ratios saying the same things
differently or saying different things?
"""
m = getPoemModel()
poems = m.poems
scores = getLogAverageCommentLength()
makePlots(poems, scores, "log of average comment length", "../experiments/exp03.pdf")
runPredictCV(poems, scores, DEFAULT_FEATURE_LIST)
def exp12():
affect = getAffectRatios()
cLength = getLogAverageCommentLength()
typeToken = getCommentTypeTokenRatio(100)
plt.figure(num=None, figsize=(18, 4.5), dpi=80, facecolor="w", edgecolor="k")
plt.subplot(1, 3, 1)
checkCorrelation(affect, cLength, "affect ratio", "log average comment length")
plt.subplot(1, 3, 2)
checkCorrelation(affect, typeToken, "affect ratio", "type-token ratio")
plt.subplot(1, 3, 3)
checkCorrelation(cLength, typeToken, "log average comment length", "type-token ratio")
plt.savefig("../experiments/exp12.pdf", format="pdf")
