-
Notifications
You must be signed in to change notification settings - Fork 1
/
functions.py
167 lines (125 loc) · 6.31 KB
/
functions.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
# functions.py
import pandas as pd
import pickle
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier, RandomForestRegressor
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
import streamlit as st
def create_category_columns(df):
# Define percentiles for categorization
low_threshold_N = df['N'].quantile(0.33)
high_threshold_N = df['N'].quantile(0.67)
# Create a new column 'N_category' based on the thresholds
df['N_category'] = pd.cut(df['N'], bins=[-float('inf'), low_threshold_N, high_threshold_N, float('inf')],
labels=['Low', 'Moderate', 'High'], include_lowest=True)
# Define percentiles for categorization
low_threshold_K = df['K'].quantile(0.33)
high_threshold_K = df['K'].quantile(0.67)
# Create a new column 'K_category' based on the thresholds
df['K_category'] = pd.cut(df['K'], bins=[-float('inf'), low_threshold_K, high_threshold_K, float('inf')],
labels=['Low', 'Moderate', 'High'], include_lowest=True)
# Define percentiles for categorization
low_threshold_P = df['P'].quantile(0.33)
high_threshold_P = df['P'].quantile(0.67)
# Create a new column 'P_category' based on the thresholds
df['P_category'] = pd.cut(df['P'], bins=[-float('inf'), low_threshold_P, high_threshold_P, float('inf')],
labels=['Low', 'Moderate', 'High'], include_lowest=True)
return df
def train_and_save_n_category(df):
# Features and target variable
X = df[['humidity', 'temperature', 'rainfall', 'ph', 'id']]
y = df['N_category']
# Scale the features
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
# Create and train the Gradient Boosting Classifier model
gb_classifier = GradientBoostingClassifier(random_state=42)
gb_classifier.fit(X_scaled, y)
# Save the model and scaler
pickle.dump(gb_classifier, open('models/gb_n_category_classifier.pkl', 'wb'))
pickle.dump(scaler, open('models/scaler_n_category.pkl', 'wb'))
def predict_n_category(humidity, temperature, rainfall, ph, id):
# Load the model and scaler
gb_classifier = pickle.load(open('models/gb_n_category_classifier.pkl', 'rb'))
scaler = pickle.load(open('models/scaler_n_category.pkl', 'rb'))
# Scale the input values
input_scaled = scaler.transform([[humidity, temperature, rainfall, ph, id]])
# Make predictions
predicted_n_category = gb_classifier.predict(input_scaled)
return predicted_n_category[0]
def train_and_save_K_category(df):
# Features and target variable
X = df[['humidity', 'temperature', 'rainfall', 'ph', 'id']]
y = df['K_category']
# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Scale the features
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)
# Create and train the Random Forest Classifier model
rf_classifier = RandomForestClassifier(random_state=42)
rf_classifier.fit(X_train_scaled, y_train)
# Save the model and scaler
pickle.dump(rf_classifier, open('models/rf_K_category_classifier.pkl', 'wb'))
pickle.dump(scaler, open('models/scaler_K_category.pkl', 'wb'))
def predict_K_category(humidity, temperature, rainfall, ph, id):
# Load the model and scaler
rf_classifier = pickle.load(open('models/rf_K_category_classifier.pkl', 'rb'))
scaler = pickle.load(open('models/scaler_K_category.pkl', 'rb'))
# Scale the input values
input_scaled = scaler.transform([[humidity, temperature, rainfall, ph, id]])
# Make predictions
predicted_K_category = rf_classifier.predict(input_scaled)
return predicted_K_category[0]
def train_and_save_P_category(df):
# Features and target variable
X = df[['humidity', 'temperature', 'rainfall', 'ph', 'id']]
y = df['P_category']
# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Scale the features
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)
# Create and train the Random Forest Classifier model
rf_classifier = RandomForestClassifier(random_state=42)
rf_classifier.fit(X_train_scaled, y_train)
# Save the model and scaler
pickle.dump(rf_classifier, open('models/rf_P_category_classifier.pkl', 'wb'))
pickle.dump(scaler, open('models/scaler_P_category.pkl', 'wb'))
def predict_P_category(humidity, temperature, rainfall, ph, id):
# Load the model and scaler
rf_classifier = pickle.load(open('models/rf_P_category_classifier.pkl', 'rb'))
scaler = pickle.load(open('models/scaler_P_category.pkl', 'rb'))
# Scale the input values
input_scaled = scaler.transform([[humidity, temperature, rainfall, ph, id]])
# Make predictions
predicted_P_category = rf_classifier.predict(input_scaled)
return predicted_P_category[0]
def train_and_save_N(df):
# Features and target variable
X = df[['humidity', 'temperature', 'rainfall', 'ph', 'id']]
y = df['N']
# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Scale the features
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)
# Create and train the Random Forest Regressor model
rf_model1 = RandomForestRegressor(random_state=42)
rf_model1.fit(X_train_scaled, y_train)
# Save the model and scaler
pickle.dump(rf_model1, open('models/rf_N_regressor.pkl', 'wb'))
pickle.dump(scaler, open('models/scaler_N.pkl', 'wb'))
def predict_N(humidity, temperature, rainfall, ph, pid):
# Load the model and scaler
rf_model1 = pickle.load(open('models/rf_N_regressor.pkl', 'rb'))
scaler = pickle.load(open('models/scaler_N.pkl', 'rb'))
# Scale the input values
input_scaled = scaler.transform([[humidity, temperature, rainfall, ph, pid]])
# Make predictions
predicted_N = rf_model1.predict(input_scaled)
return predicted_N[0]