Explore-AI · thiyasizwekubeka · Oct 20, 2020 · Oct 20, 2020
diff --git a/.DS_Store b/.DS_Store
diff --git a/Sp.ipynb b/Sp.ipynb
diff --git a/api.py b/api.py
@@ -30,7 +30,7 @@
 # Load our model into memory.
 # Please update this path to reflect your own trained model.
 static_model = load_model(
-    path_to_model='assets/trained-models/sendy_simple_lm_regression.pkl')
+    path_to_model='../trained-models/sendy_simple_lm_regression.pkl')
 
 print ('-'*40)
 print ('Model succesfully loaded')

diff --git a/assets/.DS_Store b/assets/.DS_Store
diff --git a/assets/trained-models/.ipynb_checkpoints/Untitled-checkpoint.ipynb b/assets/trained-models/.ipynb_checkpoints/Untitled-checkpoint.ipynb
@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/assets/trained-models/Untitled.ipynb b/assets/trained-models/Untitled.ipynb
@@ -0,0 +1,52 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'/Users/khwezilokusakubeka/Documents/regression-api-team4/assets/trained-models'"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pwd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/model.py b/model.py
@@ -59,9 +59,19 @@ def _preprocess_data(data):
     # ---------------------------------------------------------------
 
     # ----------- Replace this code with your own preprocessing steps --------
-    predict_vector = feature_vector_df[['Pickup Lat','Pickup Long',
-                                        'Destination Lat','Destination Long']]
-    # ------------------------------------------------------------------------
+
+    #train = pd.read_csv("Train.csv")
+    #test = pd.read_csv("Test.csv")
+
+    new = feature_vector_df.drop(['Arrival at Destination - Day of Month',
+                    'Arrival at Destination - Weekday (Mo = 1)',
+                    'Arrival at Destination - Time', 'Distance (KM)'], 
+                    axis=1)
+    #y = np.array(new['Time from Pickup to Arrival']).reshape(-1, 1)
+
+    #df = pd.concat([new,test])
+
+    predict_vector = new.fillna(1)
 
     return predict_vector
 

diff --git a/utils/.DS_Store b/utils/.DS_Store
diff --git a/utils/data/.DS_Store b/utils/data/.DS_Store
diff --git a/utils/data/Test.csv b/utils/data/Test.csv
diff --git a/utils/data/train_data.csv → utils/data/Train.csv b/utils/data/train_data.csv → utils/data/Train.csv
diff --git a/utils/data/test_data.csv b/utils/data/test_data.csv
diff --git a/utils/request.py b/utils/request.py
@@ -25,7 +25,7 @@
 # Load data from file to send as an API POST request.
 # We prepare a DataFrame with the public test set + riders data
 # from the Zindi challenge.
-test = pd.read_csv('data/test_data.csv')
+test = pd.read_csv('data/Test.csv')
 riders = pd.read_csv('data/riders.csv')
 test = test.merge(riders, how='left', on='Rider Id')
 
@@ -38,7 +38,7 @@
 # replace the URL below with its public IP:
 
 # url = 'http://{public-ip-address-of-remote-machine}:5000/api_v0.1'
-url = 'http://127.0.0.1:5000/api_v0.1'
+url = 'http://176.34.142.77:5000/api_v0.1'
 
 # Perform the POST request.
 print(f"Sending POST request to web server API at: {url}")

diff --git a/utils/train_model.py b/utils/train_model.py
@@ -10,25 +10,59 @@
 """
 
 # Dependencies
+ #%matplotlib notebook
+import numpy as np
 import pandas as pd
-import pickle
+import matplotlib.pyplot as plt
+import seaborn as sns
+from mpl_toolkits.mplot3d import Axes3D
+from sklearn.compose import ColumnTransformer
+from sklearn.preprocessing import OneHotEncoder
+from sklearn.preprocessing import LabelEncoder
+from sklearn.model_selection import train_test_split
 from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_squared_error
+import pickle
 
 # Fetch training data and preprocess for modeling
-train = pd.read_csv('data/train_data.csv')
-riders = pd.read_csv('data/riders.csv')
-train = train.merge(riders, how='left', on='Rider Id')
+train = pd.read_csv("data/Train.csv")
+test = pd.read_csv("data/Test.csv")
+
+new = train.drop(['Arrival at Destination - Day of Month',
+                  'Arrival at Destination - Weekday (Mo = 1)',
+                  'Arrival at Destination - Time', 'Distance (KM)'], 
+                 axis=1)
+y = np.array(new['Time from Pickup to Arrival']).reshape(-1, 1)
+df = pd.concat([new,test])
+df_1 = df.fillna(1)
+
+df_2 = df.drop(['Order No', 'User Id', 'Vehicle Type', 'Rider Id','Placement - Weekday (Mo = 1)', 'Confirmation - Day of Month', 'Confirmation - Weekday (Mo = 1)', 'Arrival at Pickup - Day of Month', 'Arrival at Pickup - Weekday (Mo = 1)', 'Pickup - Day of Month','Pickup - Weekday (Mo = 1)', 'Placement - Time', 'Confirmation - Time', 'Arrival at Pickup - Time', 'Pickup - Time'], axis = 1)
+df_2 = df_2.fillna(1)
+df_2 = pd.get_dummies(df_2, drop_first=True)
+X = df_2[:len(train)]
+Y = df_2[len(train):]
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)
 
-y_train = train[['Time from Pickup to Arrival']]
-X_train = train[['Pickup Lat','Pickup Long',
-                 'Destination Lat','Destination Long']]
 
 # Fit model
-lm_regression = LinearRegression(normalize=True)
+regressor = LinearRegression()
 print ("Training Model...")
-lm_regression.fit(X_train, y_train)
+regressor.fit(X_train, y_train)
+pred = regressor.predict(X_test)
+
+
+def rmse(y_test, y_predict):
+    return np.sqrt(mean_squared_error(y_test, y_predict))
+
+rmse(y_test, pred)
+
+y_pred = regressor.predict(Y)
+test = test.fillna(0)
+
+test_1 = test[['Order No']]
+test_1['Time from Pickup to Arrival'] = y_pred
 
 # Pickle model for use within our API
 save_path = '../trained-models/sendy_simple_lm_regression.pkl'
 print (f"Training completed. Saving model to: {save_path}")
-pickle.dump(lm_regression, open(save_path,'wb'))
+pickle.dump(regressor, open(save_path,'wb'))
diff --git a/utils/untitled b/utils/untitled