def run_num_correlations(question_pairs, data):
print("Running correlations.")
correlation_results = []
for t in question_pairs:
full_response_entries = tools.get_responses_to_numbers(t, data)
answers_1, answers_2 = tools.extract_vals_from_responses(*full_response_entries)
invalid_1, invalid_2 = tools.get_indexes_of_invalid_repsonse_types(
[int], answers_1, answers_2
)
invalid_all = tools.merge_invalid_indexes(invalid_1, invalid_2)
final_answers_1, final_answers_2 = tools.remove_entries_at_indexes(
invalid_all, answers_1, answers_2)
# print(answers_1, answers_2)
# print(final_answers_1, final_answers_2)
# print(len(answers_1), len(answers_2))
# print(len(final_answers_1), len(final_answers_2))
slope, intercept, r_value, p_value, std_err = stats.linregress(
final_answers_1, final_answers_2
)
r_squared = r_value**2
result = {"questions": t, "slope": slope, "intercept": intercept,
"r_value": r_value, "p_value": p_value, "std_err": std_err,
"r_squared": r_squared
}
correlation_results.append(result)
print("Finished running correlations.")
return correlation_results
def plot_correlations(results, data, pdf):
print("Saving {} result plots to pdf.".format(len(results)))
for result in results:
print('.'),
sys.stdout.flush()
q1, q2 = result['questions']
title_1 = tools.get_question_title(q1, data)
title_2 = tools.get_question_title(q2, data)
x_raw = tools.get_responses_to_number(q1, data)
y_raw = tools.get_responses_to_number(q2, data)
x,y = tools.extract_vals_from_responses(x_raw, y_raw)
invalid_x, invalid_y = tools.get_indexes_of_invalid_repsonse_types(
[int], x, y
)
invalid_all = tools.merge_invalid_indexes(invalid_x, invalid_y)
x, y = tools.remove_entries_at_indexes(invalid_all, x, y)
# Calculate the point density
xy = np.vstack([x,y])
try:
z = stats.gaussian_kde(xy)(xy)
except Exception as e:
print(xy)
raise e
size = 5000*z
final_size = []
for s in size:
final_size.append(max(s,60))
# Calculate axis numbers
x_range = (min(x)-1, max(x)+1)
y_range = (min(y)-1, max(y)+1)
# generate data for best fit line
slope = result['slope']
intercept = result['intercept']
x_fit_points = x_range
y_fit_points = (x_range[0]*slope + intercept, x_range[1]*slope + intercept)
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.set_title("{} vs {}\nr_squared = {:.4f}".format(title_1, title_2, result['r_squared']))
ax.set_xlabel("{} (Q{})".format(title_1, q1))
ax.set_ylabel("{} (Q{})".format(title_2, q2))
ax.scatter(x, y, c=z, s=final_size, edgecolor='')
ax.plot(x_fit_points, y_fit_points, '-')
pdf.savefig(fig)
plt.close(fig)
print("\nDone saving plots to pdf.\n")
