File size: 4,299 Bytes
42193eb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e0adc3b
42193eb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
086c1bf
42193eb
 
086c1bf
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
### ----------------------------- ###
###           libraries           ###
### ----------------------------- ###

import gradio as gr
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn import metrics
from reader import get_article


### ------------------------------ ###
###       data transformation      ###
### ------------------------------ ###

# load dataset
uncleaned_data = pd.read_csv('data.csv')

# remove timestamp from dataset (always first column)
uncleaned_data = uncleaned_data.iloc[: , 1:]
data = pd.DataFrame()

# keep track of which columns are categorical and what 
# those columns' value mappings are
# structure: {colname1: {...}, colname2: {...} }
cat_value_dicts = {}
final_colname = uncleaned_data.columns[len(uncleaned_data.columns) - 1]

# for each column...
for (colname, colval) in uncleaned_data.iteritems():

  # check if col is already a number; if so, add col directly
  # to new dataframe and skip to next column
  if isinstance(colval.values[0], (np.integer, float)):
    data[colname] = uncleaned_data[colname].copy()
    continue

  # structure: {0: "lilac", 1: "blue", ...}
  new_dict = {}
  val = 0 # first index per column
  transformed_col_vals = [] # new numeric datapoints

  # if not, for each item in that column...
  for (row, item) in enumerate(colval.values):
    
    # if item is not in this col's dict...
    if item not in new_dict:
      new_dict[item] = val
      val += 1
    
    # then add numerical value to transformed dataframe
    transformed_col_vals.append(new_dict[item])
  
  # reverse dictionary only for final col (0, 1) => (vals)
  if colname == final_colname:
    new_dict = {value : key for (key, value) in new_dict.items()}

  cat_value_dicts[colname] = new_dict
  data[colname] = transformed_col_vals


### -------------------------------- ###
###           model training         ###
### -------------------------------- ###

# select features and predicton; automatically selects last column as prediction
cols = len(data.columns)
num_features = cols - 1
x = data.iloc[: , :num_features]
y = data.iloc[: , num_features:]

# split data into training and testing sets
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25)

# instantiate the model (using default parameters)
model = LogisticRegression()
model.fit(x_train, y_train.values.ravel())
y_pred = model.predict(x_test)


### -------------------------------- ###
###        article generation        ###
### -------------------------------- ###
# borrow file reading function from reader.py

def get_feat():
  feats = [abs(x) for x in model.coef_[0]]
  max_val = max(feats)
  idx = feats.index(max_val)
  return data.columns[idx]
  
acc = str(round(metrics.accuracy_score(y_test, y_pred) * 100, 1)) + '%**'
most_imp_feat = get_feat() + "**"
info = get_article(acc, most_imp_feat)



### ------------------------------- ###
###        interface creation       ###
### ------------------------------- ###


# predictor for generic number of features
def general_predictor(*args):
  features = []

  # transform categorical input
  for colname, arg in zip(data.columns, args):
    if (colname in cat_value_dicts):
      features.append(cat_value_dicts[colname][arg])
    else:
      features.append(arg)

  # predict single datapoint
  new_input = [features]
  result = model.predict(new_input)
  return cat_value_dicts[final_colname][result[0]]

# add data labels to replace those lost via star-args
inputls = []
for colname in data.columns:
  # skip last column
  if colname == final_colname:
    continue

  # access categories dict if data is categorical
  # otherwise, just use a number input
  if colname in cat_value_dicts:
    radio_options = list(cat_value_dicts[colname].keys())
    inputls.append(gr.inputs.Radio(choices=radio_options, type="value", label=colname))
  else:
    # add numerical input
    inputls.append(gr.inputs.Number(label=colname))
  
# generate gradio interface
interface = gr.Interface(general_predictor, inputs=inputls, outputs="text", article=info['article'], css=info['css'], theme="grass", title=info['title'], allow_flagging='never', description=info['description'])

# show the interface 
interface.launch()