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 exp08():
"""
If high affect ratio comments are less rich in their analysis/observation,
does this imply that they have a lower type-token ratio? Actually, this
cannot be well predicted. (~0% reduction in accuracy)
"""
m = getPoemModel()
poems = m.poems
scores = getCommentTypeTokenRatio()
makePlots(poems, scores, "comment type token ratio", "../experiments/exp08.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")
def exp081():
"""
Repeat exp 8, but sample from all of the words. This should control for the
fact that longer documents tend to have lower type-token ratios. We can
predict this with ~15% reduction in error.
This suggests that "richness" of response can be categorized by the type-
token ratio, though this is not so easily predicted as affect ratio. With
experiment 3, we know that we can predict the log of comment length with
~10% accuracy.
Taking note of the sign of the correlation of each variable, this gives us
a definition of 'richness' that includes:
- longer comments
- higher type-token ratio
- lower affect ratio
"""
m = getPoemModel()
poems = m.poems
scores = getCommentTypeTokenRatio(100) # sample words
makePlots(poems, scores, "sampled type-token ratio", "../experiments/exp08.1.pdf")
runPredictCV(poems, scores, DEFAULT_FEATURE_LIST)
