/
app.py
284 lines (180 loc) · 8.19 KB
/
app.py
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
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
"""Code for our api app"""
from flask import Flask, jsonify, request
import basilica
import numpy as np
import pandas as pd
from scipy import spatial
app = Flask(__name__)
@app.route('/')
def root():
return "We have the best API!"
@app.route('/strains', methods=['Post'])
def strains():
""" a route, expects json object with 1 key """
# receive input
lines = request.get_json(force=True)
# get data from json
text = lines['input'] # json keys to be determined
# validate input (optional)
assert isinstance(text, str)
# predict
output = predict(text)
# give output to sender.
return output
@app.route('/symptom', methods=['Post'])
def symptom():
""" a route, expects json object with 1 key """
# receive input
lines = request.get_json(force=True)
# get data from json
text = lines['input'] # json keys to be determined
# validate input (optional)
assert isinstance(text, str)
# predict
output = predict_symptoms(text)
# give output to sender.
return output
@app.route('/general', methods=['Post'])
def general():
""" a route, expects json object with 1 key """
# receive input
lines = request.get_json(force=True)
# get data from json
text = lines['input'] # json keys to be determined
# validate input (optional)
assert isinstance(text, str)
# predict
output = predict_all(text)
# give output to sender.
return output
# 4 spaced symptoms json version
# user input
user_input_symp = "multiple sclerosis, epilepsy, pain, "
def predict_symptoms(user_input_symp):
#unpickling file of embedded cultivar symptoms diseases
unpickled_df_test = pd.read_pickle("./symptommedembedv8.pkl")
# getting data
df = pd.read_csv('symptoms8_medcab3.csv')
# Part 1
# a function to calculate_user_text_embedding
# to save the embedding value in session memory
user_input_embedding = 0
def calculate_user_text_embedding(input, user_input_embedding):
# setting a string of two sentences for the algo to compare
sentences = [input]
# calculating embedding for both user_entered_text and for features
with basilica.Connection('36a370e3-becb-99f5-93a0-a92344e78eab') as c:
user_input_embedding = list(c.embed_sentences(sentences))
return user_input_embedding
# run the function to save the embedding value in session memory
user_input_embedding = calculate_user_text_embedding(user_input, user_input_embedding)
# part 2
score = 0
def score_user_input_from_stored_embedding_from_stored_values(input, score, row1, user_input_embedding):
# obtains pre-calculated values from a pickled dataframe of arrays
embedding_stored = unpickled_df_test.loc[row1, 0]
# calculates the similarity of user_text vs. product description
score = 1 - spatial.distance.cosine(embedding_stored, user_input_embedding)
# returns a variable that can be used outside of the function
return score
# Part 3
for i in range(2351):
# calls the function to set the value of 'score'
# which is the score of the user input
score = score_user_input_from_stored_embedding_from_stored_values(user_input_symp, score, i, user_input_embedding)
#stores the score in the dataframe
df.loc[i,'score'] = score
# Part 4: returns all data for the top 5 results as a json obj
df_big_json = df.sort_values(by='score', ascending=False)
df_big_json = df_big_json.drop(['Unnamed: 0', 'Unnamed: 0.1'], axis = 1)
df_big_json = df_big_json[:5]
df_big_json = df_big_json.to_json(orient='columns')
# Part 5: output
return df_big_json
# 4 spaced effect json version
# user input
user_input = "text, Relaxed, Violet, Aroused, Creative, Happy, Energetic, Flowery, Diesel"
def predict(user_input):
# getting data
df = pd.read_csv('symptoms8_medcab3.csv')
#effcts unpickling file of embedded cultivar descriptions
unpickled_df_test = pd.read_pickle("./medembedv2.pkl")
# Part 1
# a function to calculate_user_text_embedding
# to save the embedding value in session memory
user_input_embedding = 0
def calculate_user_text_embedding(input, user_input_embedding):
# setting a string of two sentences for the algo to compare
sentences = [input]
# calculating embedding for both user_entered_text and for features
with basilica.Connection('36a370e3-becb-99f5-93a0-a92344e78eab') as c:
user_input_embedding = list(c.embed_sentences(sentences))
return user_input_embedding
# run the function to save the embedding value in session memory
user_input_embedding = calculate_user_text_embedding(user_input, user_input_embedding)
# part 2
score = 0
def score_user_input_from_stored_embedding_from_stored_values(input, score, row1, user_input_embedding):
# obtains pre-calculated values from a pickled dataframe of arrays
embedding_stored = unpickled_df_test.loc[row1, 0]
# calculates the similarity of user_text vs. product description
score = 1 - spatial.distance.cosine(embedding_stored, user_input_embedding)
# returns a variable that can be used outside of the function
return score
# Part 3
for i in range(2351):
# calls the function to set the value of 'score'
# which is the score of the user input
score = score_user_input_from_stored_embedding_from_stored_values(user_input, score, i, user_input_embedding)
#stores the score in the dataframe
df.loc[i,'score'] = score
# Part 4: returns all data for the top 5 results as a json obj
df_big_json = df.sort_values(by='score', ascending=False)
df_big_json = df_big_json.drop(['Unnamed: 0', 'Unnamed: 0.1'], axis = 1)
df_big_json = df_big_json[:5]
df_big_json = df_big_json.to_json(orient='columns')
# Part 5: output
return df_big_json
# user input
user_input = "multiple sclerosis, epilepsy, pain, "
def predict_all(user_input_all):
#unpickling file of embedded cultivar symptoms diseases
unpickled_df_test = pd.read_pickle("./all_text_medembedv8.pkl")
# getting data
df = pd.read_csv('symptoms8_medcab3.csv')
# Part 1
# a function to calculate_user_text_embedding
# to save the embedding value in session memory
user_input_embedding = 0
def calculate_user_text_embedding(input, user_input_embedding):
# setting a string of two sentences for the algo to compare
sentences = [input]
# calculating embedding for both user_entered_text and for features
with basilica.Connection('36a370e3-becb-99f5-93a0-a92344e78eab') as c:
user_input_embedding = list(c.embed_sentences(sentences))
return user_input_embedding
# run the function to save the embedding value in session memory
user_input_embedding = calculate_user_text_embedding(user_input_all, user_input_embedding)
# part 2
score = 0
def score_user_input_from_stored_embedding_from_stored_values(input, score, row1, user_input_embedding):
# obtains pre-calculated values from a pickled dataframe of arrays
embedding_stored = unpickled_df_test.loc[row1, 0]
# calculates the similarity of user_text vs. product description
score = 1 - spatial.distance.cosine(embedding_stored, user_input_embedding)
# returns a variable that can be used outside of the function
return score
# Part 3
for i in range(2351):
# calls the function to set the value of 'score'
# which is the score of the user input
score = score_user_input_from_stored_embedding_from_stored_values(user_input, score, i, user_input_embedding)
#stores the score in the dataframe
df.loc[i,'score'] = score
# Part 4: returns all data for the top 5 results as a json obj
df_big_json = df.sort_values(by='score', ascending=False)
df_big_json = df_big_json.drop(['Unnamed: 0', 'Unnamed: 0.1'], axis = 1)
df_big_json = df_big_json[:5]
df_big_json = df_big_json.to_json(orient='columns')
# Part 5: output
return df_big_json