def distribution(excel_rows, item_name, items, file_name):
# Using 95% confidence interval
# (1-0.95)/2
Z_score = abs(st.norm.ppf(0.025))
alpha = 1 - 0.95
data_files = {}
# create dataframe
for item in items:
if item_name == "Monkey":
df = (monkey_df[(monkey_df.Monkey == item)])
elif item_name == "gender":
df = (gender_df[(gender_df.gender == item)])
z = BayesianEstimator(model, df)
cat_cpd = z.estimate_cpd('Category',
prior_type="bdeu",
equivalent_sample_size=0) # .to_factor()
for condition in conditions:
for category in categories:
try:
count = list(
z.state_counts('Category')
[condition].to_dict().values())[0][category]
# count = z.state_counts('Category')[condition][category][category]
prob = cat_cpd.get_value(**{
'Condition': condition,
'Category': category
})
# print(prob)
# p_hat and q_hat set to conservative since we have no previous data #0.5 for each
# Since its probability I clip to 0
lower_ci = max(
prob - Z_score * math.sqrt((0.5 * 0.5) / df.shape[0]),
0)
upper_ci = prob + Z_score * math.sqrt(
(0.5 * 0.5) / df.shape[0])
if not isNaN(prob) and prob > 0:
excel_rows.append([
item, condition, category, count, prob, lower_ci,
upper_ci, alpha
])
else:
pass
# excel_rows.append([item, left, right, cat, count, prob, 0, 0, 0])
except KeyError:
pass
# excel_rows.append([item, left, right, cat, count, 0, 0 , 0, 0])
prob_df = pd.DataFrame.from_records(excel_rows[1:], columns=excel_rows[0])
writer = pd.ExcelWriter(file_name + ".xlsx")
prob_df.to_excel(writer, sheet_name='Distribution')
prob_df.sort_values('Probability', ascending=True).drop_duplicates(
[item_name]).to_excel(writer, sheet_name='prefference')
writer.save()
return prob_df
def distribution(excel_rows, item_name, items, file_name, df_cols,
groupby_cols, bp_group):
# Using 95% confidence interval
# (1-0.95)/2
Z_score = abs(st.norm.ppf(0.025))
alpha = 1 - 0.95
data_files = {}
Orientations = ["left", "right"]
# create dataframe
for item in items:
if item_name == "Monkey":
df = (monkey_df[(monkey_df.Monkey == item)])
elif item_name == "gender":
df = (gender_df[(gender_df.gender == item)])
z = BayesianEstimator(model, df)
cat_cpd = z.estimate_cpd('Orientation',
prior_type="bdeu",
equivalent_sample_size=6) # .to_factor()
for left in categories:
for right in categories:
for cat in Orientations:
try:
count = z.state_counts('Orientation')[left][right][cat]
prob = cat_cpd.get_value(
**{
'Left_categ': left,
'Right_categ': right,
'Orientation': cat
})
# p_hat and q_hat set to conservative since we have no previous data #0.5 for each
# Since its probability I clip to 0
lower_ci = max(
prob - Z_score * math.sqrt(
(0.5 * 0.5) / df.shape[0]), 0)
upper_ci = prob + Z_score * math.sqrt(
(0.5 * 0.5) / df.shape[0])
if not isNaN(prob) and prob > 0:
excel_rows.append([
item, left, right, cat, count, prob, lower_ci,
upper_ci, alpha
])
else:
pass
# excel_rows.append([item, left, right, cat, count, prob, 0, 0, 0])
except KeyError:
pass
# excel_rows.append([item, left, right, cat, count, 0, 0 , 0, 0])
prob_df = pd.DataFrame.from_records(excel_rows[1:], columns=excel_rows[0])
gen_df = prob_df[df_cols].groupby(groupby_cols)['Count'].agg(
['sum']) # .reset_index()
ax, bp = gen_df.boxplot(rot=90,
fontsize=12,
figsize=(16, 10),
column=['sum'],
by=bp_group,
return_type="both")[0]
plt.title(item_name.capitalize() + " Box plot grouped by : " +
str(bp_group))
plt.suptitle('')
plt.ylabel("sum")
# group = ['Left-Category', 'Category']
# ax, bp = gen_df.boxplot(rot=90, fontsize=12, figsize=(24, 12), column=['sum'], by=group, return_type="both")[0]
# plt.title("Box plot grouped by : " + str(group))
# plt.suptitle('')
# plt.ylabel("sum")
#
#
# group = ['Right-Category', 'Category']
# ax, bp = gen_df.boxplot(rot=90, fontsize=12, figsize=(24, 12), column=['sum'], by=group, return_type="both")[0]
# plt.title("Box plot grouped by : " + str(group))
# plt.suptitle('')
# plt.ylabel("sum")
writer = pd.ExcelWriter(file_name + ".xlsx")
prob_df.to_excel(writer, sheet_name='Distribution')
prob_df.sort_values('Probability', ascending=False).drop_duplicates(
[item_name]).to_excel(writer, sheet_name='prefference')
writer.save()
plt.savefig(file_name + ".png", dpi=100)
plt.show()
plt.clf()