prabhant

From Ian Oszwald talk @pyconUK 2017

• Yellowbrick: for visualisations
• ELI5:

prabhant

import matplotlib.pyplot as plt

import numpy as np

from numpy import genfromtxt
#genfromtxt('my_file.csv', delimiter=',')
 

# Set the random seed for data generation

prabhant

 with open('indlib8.csv') as f:
   ...:     reader = csv.reader(f)
   ...:     for row in reader:
   ...:         p = Indicator()             
   ...:         arr.append(p)
   ...:         p.save()

  p = Indicator(level = row[0], sector =row[5], subsector=row[6], number = row[1], definition = row[7],justification = row[8], unit_of_measure = row[9], disaggregation = row[11], direction_of_change = row[12], baseline = row[13], rationale_for_target = row[15], means_of_verification = row[16], question_format = row[17], data_collection_method = row[18], denominator = row[20], numnerator = row[21], responsible_person = row[22], methods_of_analysis = row[23], information_use = row[24], quality_assurance = row[26], data_issues = row[27],indicator_changes = row[28], comments = row[29])

                               

prabhant

from dash.dependencies import Input, Output
import dash_html_components as html
import dash_core_components as dcc
import pandas as pd

app = dash.Dash()
app.layout = html.Div([
    html.H1('Please enter the input'),
    dcc.Input(id='my-id', value='initial value', type='text'),
    html.Div(id='my-div')

prabhant

app.layout = html.Div([
                    html.H2('Tolareports'),
                    dcc.Dropdown(
                        value='2017',
                        options=[{'label': i, 'value': i} for i in ['2017', '2018']],
                        multi=False,
                        id='dropdown-year',
                        placeholder="Select Year",),
                     dcc.Graph(id = 'table-1-1'),
                     dcc.Graph(id = 'table-1-2'),

prabhant

---------------------------------------------------------------------------

OpenMLServerException                     Traceback (most recent call last)

<ipython-input-8-b6154457ed10> in <module>()
      6 run = openml.runs.run_model_on_task(model, task, avoid_duplicate_runs=False)
      7 # Publish the experiment on OpenML (optional, requires an API key).
----> 8 run.publish()
      9 
     10 print('URL for run: %s/run/%d' % (openml.config.server, run.run_id))

prabhant

#Code for entire dataset to pyarrow table
import pyarrow as pa
import pyarrow.parquet as pq

# getting the dataset
did=39947

d = openml.datasets.get_dataset(did, download_qualities=False)
df , *_ = d.get_data(dataset_format="dataframe", include_row_id=True, include_ignore_attribute=True)
df = df[[f.name for f in d.features.values()]]

prabhant

p = Pipeline(steps=[('imputation', SimpleImputer(strategy='median')),('1', SMOTE(k_neighbors=21)),('0', EasyEnsembleClassifier(n_estimators=100))])
try:
  if p['imputation']:
    p = p[1:]
except:
  pass

print(p)
l = []
for i in range(len(p)):

prabhant

import openml

t = openml.runs.get_run_trace(10437679)
l = list()

for ts in t.trace_iterations.keys():
    d1 = t.trace_iterations[ts].__dict__
    d2 = t.trace_iterations[ts].get_parameters()
    d1.pop('setup_string')
    d3 = {**d1, **d2}