'age', 'workclass', 'education_num', 'marital_status', 'post',
'relationship', 'nation', 'gender', 'capital', 'hours_per_week',
'country', 'wealth'
]
for column in columns_name:
encode_labels = label_encode(column)
label_encode_features.append(encode_labels)
data = combine_features_tuples(label_encode_features)
df = DataFrame(data, columns=columns_name)
df.cumsum().plot()
plt.savefig("outs\\cumsum.png")
plt.close()
df.diff().hist()
plt.savefig("outs\\diff_hist.png")
plt.close()
for col in columns_name:
df[col].plot.box()
plt.savefig("outs\\boxes\\{}.png".format(col))
plt.close()
for col in columns_name:
result = sql_manager.crs.execute((
"select distinct {},count({}) from information group by {}".format(
col, col, col))).fetchall()
counts = [x[1] for x in result]
attr = [x[0] for x in result]
fig1, ax1 = plt.subplots()
