Commit
•
d26fc7e
1
Parent(s):
3cef44d
Delete app.py
Browse files
app.py
DELETED
@@ -1,172 +0,0 @@
|
|
1 |
-
### ----------------------------- ###
|
2 |
-
### libraries ###
|
3 |
-
### ----------------------------- ###
|
4 |
-
|
5 |
-
import gradio as gr
|
6 |
-
import pandas as pd
|
7 |
-
import numpy as np
|
8 |
-
from sklearn.model_selection import train_test_split
|
9 |
-
from sklearn.linear_model import LogisticRegression
|
10 |
-
from sklearn import metrics
|
11 |
-
|
12 |
-
|
13 |
-
### ------------------------------ ###
|
14 |
-
### data transformation ###
|
15 |
-
### ------------------------------ ###
|
16 |
-
|
17 |
-
# load dataset
|
18 |
-
uncleaned_data = pd.read_csv('data.csv')
|
19 |
-
|
20 |
-
# remove timestamp from dataset (always first column)
|
21 |
-
uncleaned_data = uncleaned_data.iloc[: , 1:]
|
22 |
-
data = pd.DataFrame()
|
23 |
-
|
24 |
-
# keep track of which columns are categorical and what
|
25 |
-
# those columns' value mappings are
|
26 |
-
# structure: {colname1: {...}, colname2: {...} }
|
27 |
-
cat_value_dicts = {}
|
28 |
-
final_colname = uncleaned_data.columns[len(uncleaned_data.columns) - 1]
|
29 |
-
|
30 |
-
# for each column...
|
31 |
-
for (colname, colval) in uncleaned_data.iteritems():
|
32 |
-
|
33 |
-
# check if col is already a number; if so, add col directly
|
34 |
-
# to new dataframe and skip to next column
|
35 |
-
if isinstance(colval.values[0], (np.integer, float)):
|
36 |
-
data[colname] = uncleaned_data[colname].copy()
|
37 |
-
continue
|
38 |
-
|
39 |
-
# structure: {0: "lilac", 1: "blue", ...}
|
40 |
-
new_dict = {}
|
41 |
-
val = 0 # first index per column
|
42 |
-
transformed_col_vals = [] # new numeric datapoints
|
43 |
-
|
44 |
-
# if not, for each item in that column...
|
45 |
-
for (row, item) in enumerate(colval.values):
|
46 |
-
|
47 |
-
# if item is not in this col's dict...
|
48 |
-
if item not in new_dict:
|
49 |
-
new_dict[item] = val
|
50 |
-
val += 1
|
51 |
-
|
52 |
-
# then add numerical value to transformed dataframe
|
53 |
-
transformed_col_vals.append(new_dict[item])
|
54 |
-
|
55 |
-
# reverse dictionary only for final col (0, 1) => (vals)
|
56 |
-
if colname == final_colname:
|
57 |
-
new_dict = {value : key for (key, value) in new_dict.items()}
|
58 |
-
|
59 |
-
cat_value_dicts[colname] = new_dict
|
60 |
-
data[colname] = transformed_col_vals
|
61 |
-
|
62 |
-
|
63 |
-
### -------------------------------- ###
|
64 |
-
### model training ###
|
65 |
-
### -------------------------------- ###
|
66 |
-
|
67 |
-
# select features and predicton; automatically selects last column as prediction
|
68 |
-
cols = len(data.columns)
|
69 |
-
num_features = cols - 1
|
70 |
-
x = data.iloc[: , :num_features]
|
71 |
-
y = data.iloc[: , num_features:]
|
72 |
-
|
73 |
-
# split data into training and testing sets
|
74 |
-
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25)
|
75 |
-
|
76 |
-
# instantiate the model (using default parameters)
|
77 |
-
model = LogisticRegression()
|
78 |
-
model.fit(x_train, y_train.values.ravel())
|
79 |
-
y_pred = model.predict(x_test)
|
80 |
-
|
81 |
-
|
82 |
-
### -------------------------------- ###
|
83 |
-
### article generation ###
|
84 |
-
### -------------------------------- ###
|
85 |
-
# borrow file reading function from reader.py
|
86 |
-
|
87 |
-
def get_feat():
|
88 |
-
feats = [abs(x) for x in model.coef_[0]]
|
89 |
-
max_val = max(feats)
|
90 |
-
idx = feats.index(max_val)
|
91 |
-
return data.columns[idx]
|
92 |
-
|
93 |
-
acc = str(round(metrics.accuracy_score(y_test, y_pred) * 100, 1)) + "%"
|
94 |
-
most_imp_feat = get_feat()
|
95 |
-
# info = get_article(acc, most_imp_feat)
|
96 |
-
|
97 |
-
|
98 |
-
|
99 |
-
### ------------------------------- ###
|
100 |
-
### interface creation ###
|
101 |
-
### ------------------------------- ###
|
102 |
-
|
103 |
-
|
104 |
-
# predictor for generic number of features
|
105 |
-
def general_predictor(*args):
|
106 |
-
features = []
|
107 |
-
|
108 |
-
# transform categorical input
|
109 |
-
for colname, arg in zip(data.columns, args):
|
110 |
-
if (colname in cat_value_dicts):
|
111 |
-
features.append(cat_value_dicts[colname][arg])
|
112 |
-
else:
|
113 |
-
features.append(arg)
|
114 |
-
|
115 |
-
# predict single datapoint
|
116 |
-
new_input = [features]
|
117 |
-
result = model.predict(new_input)
|
118 |
-
return cat_value_dicts[final_colname][result[0]]
|
119 |
-
|
120 |
-
# add data labels to replace those lost via star-args
|
121 |
-
|
122 |
-
|
123 |
-
block = gr.Blocks()
|
124 |
-
|
125 |
-
with open('info.md') as f:
|
126 |
-
with block:
|
127 |
-
gr.Markdown(f.readline())
|
128 |
-
gr.Markdown('Take the quiz to get a personalized recommendation using AI.')
|
129 |
-
|
130 |
-
with gr.Row():
|
131 |
-
with gr.Box():
|
132 |
-
inputls = []
|
133 |
-
for colname in data.columns:
|
134 |
-
# skip last column
|
135 |
-
if colname == final_colname:
|
136 |
-
continue
|
137 |
-
|
138 |
-
# access categories dict if data is categorical
|
139 |
-
# otherwise, just use a number input
|
140 |
-
if colname in cat_value_dicts:
|
141 |
-
radio_options = list(cat_value_dicts[colname].keys())
|
142 |
-
inputls.append(gr.Dropdown(radio_options, type="value", label=colname))
|
143 |
-
else:
|
144 |
-
# add numerical input
|
145 |
-
inputls.append(gr.Number(label=colname))
|
146 |
-
gr.Markdown("<br />")
|
147 |
-
|
148 |
-
submit = gr.Button("Click to see your personalized result!", variant="primary")
|
149 |
-
gr.Markdown("<br />")
|
150 |
-
output = gr.Textbox(label="Your recommendation:", placeholder="your recommendation will appear here")
|
151 |
-
|
152 |
-
submit.click(fn=general_predictor, inputs=inputls, outputs=output)
|
153 |
-
gr.Markdown("<br />")
|
154 |
-
|
155 |
-
with gr.Row():
|
156 |
-
with gr.Box():
|
157 |
-
gr.Markdown(f"<h3>Accuracy: </h3>{acc}")
|
158 |
-
with gr.Box():
|
159 |
-
gr.Markdown(f"<h3>Most important feature: </h3>{most_imp_feat}")
|
160 |
-
|
161 |
-
gr.Markdown("<br />")
|
162 |
-
|
163 |
-
with gr.Box():
|
164 |
-
gr.Markdown('''⭐ Note that model accuracy is based on the uploaded data.csv and reflects how well the AI model can give correct recommendations for <em>that dataset</em>. Model accuracy and most important feature can be helpful for understanding how the model works, but <em>should not be considered absolute facts about the real world</em>.''')
|
165 |
-
|
166 |
-
with gr.Box():
|
167 |
-
with open('info.md') as f:
|
168 |
-
f.readline()
|
169 |
-
gr.Markdown(f.read())
|
170 |
-
|
171 |
-
# show the interface
|
172 |
-
block.launch()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|