diff --git "a/6_model_deployment (Updated).ipynb" "b/6_model_deployment (Updated).ipynb" new file mode 100644--- /dev/null +++ "b/6_model_deployment (Updated).ipynb" @@ -0,0 +1,2388 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + " | property_type | \n", + "price | \n", + "location | \n", + "city | \n", + "baths | \n", + "purpose | \n", + "bedrooms | \n", + "Area_in_Marla | \n", + "
---|---|---|---|---|---|---|---|---|
108839 | \n", + "House | \n", + "13800000 | \n", + "Pak Arab Housing Society | \n", + "Lahore | \n", + "3 | \n", + "For Sale | \n", + "3 | \n", + "5.0 | \n", + "
97355 | \n", + "House | \n", + "17500000 | \n", + "Marghzar Officers Colony | \n", + "Lahore | \n", + "6 | \n", + "For Sale | \n", + "6 | \n", + "10.0 | \n", + "
125129 | \n", + "House | \n", + "12500000 | \n", + "Adiala Road | \n", + "Rawalpindi | \n", + "5 | \n", + "For Sale | \n", + "5 | \n", + "10.0 | \n", + "
155467 | \n", + "Lower Portion | \n", + "47000 | \n", + "Satellite Town | \n", + "Rawalpindi | \n", + "3 | \n", + "For Rent | \n", + "3 | \n", + "7.0 | \n", + "
81132 | \n", + "House | \n", + "7800000 | \n", + "Shalimar Housing Scheme | \n", + "Lahore | \n", + "4 | \n", + "For Sale | \n", + "3 | \n", + "4.0 | \n", + "
... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "
122491 | \n", + "House | \n", + "19000000 | \n", + "Lake City | \n", + "Lahore | \n", + "5 | \n", + "For Sale | \n", + "4 | \n", + "10.0 | \n", + "
44101 | \n", + "Upper Portion | \n", + "40000 | \n", + "Korang Town | \n", + "Islamabad | \n", + "5 | \n", + "For Rent | \n", + "4 | \n", + "20.0 | \n", + "
99634 | \n", + "House | \n", + "42500000 | \n", + "DHA Defence | \n", + "Lahore | \n", + "5 | \n", + "For Sale | \n", + "4 | \n", + "10.0 | \n", + "
147606 | \n", + "Flat | \n", + "6800000 | \n", + "Bahria Town Karachi | \n", + "Karachi | \n", + "2 | \n", + "For Sale | \n", + "2 | \n", + "4.2 | \n", + "
65106 | \n", + "House | \n", + "300000 | \n", + "F-7 | \n", + "Islamabad | \n", + "6 | \n", + "For Rent | \n", + "6 | \n", + "22.0 | \n", + "
10000 rows × 8 columns
\n", + "\n", + " | property_type | \n", + "price | \n", + "location | \n", + "city | \n", + "baths | \n", + "purpose | \n", + "bedrooms | \n", + "Area_in_Marla | \n", + "
---|---|---|---|---|---|---|---|---|
108839 | \n", + "House | \n", + "13800000 | \n", + "Pak Arab Housing Society | \n", + "Lahore | \n", + "3 | \n", + "For Sale | \n", + "3 | \n", + "5.0 | \n", + "
97355 | \n", + "House | \n", + "17500000 | \n", + "Marghzar Officers Colony | \n", + "Lahore | \n", + "6 | \n", + "For Sale | \n", + "6 | \n", + "10.0 | \n", + "
125129 | \n", + "House | \n", + "12500000 | \n", + "Adiala Road | \n", + "Rawalpindi | \n", + "5 | \n", + "For Sale | \n", + "5 | \n", + "10.0 | \n", + "
155467 | \n", + "Lower Portion | \n", + "47000 | \n", + "Satellite Town | \n", + "Rawalpindi | \n", + "3 | \n", + "For Rent | \n", + "3 | \n", + "7.0 | \n", + "
81132 | \n", + "House | \n", + "7800000 | \n", + "Shalimar Housing Scheme | \n", + "Lahore | \n", + "4 | \n", + "For Sale | \n", + "3 | \n", + "4.0 | \n", + "
... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "
122491 | \n", + "House | \n", + "19000000 | \n", + "Lake City | \n", + "Lahore | \n", + "5 | \n", + "For Sale | \n", + "4 | \n", + "10.0 | \n", + "
44101 | \n", + "Upper Portion | \n", + "40000 | \n", + "Korang Town | \n", + "Islamabad | \n", + "5 | \n", + "For Rent | \n", + "4 | \n", + "20.0 | \n", + "
99634 | \n", + "House | \n", + "42500000 | \n", + "DHA Defence | \n", + "Lahore | \n", + "5 | \n", + "For Sale | \n", + "4 | \n", + "10.0 | \n", + "
147606 | \n", + "Flat | \n", + "6800000 | \n", + "Bahria Town Karachi | \n", + "Karachi | \n", + "2 | \n", + "For Sale | \n", + "2 | \n", + "4.2 | \n", + "
65106 | \n", + "House | \n", + "300000 | \n", + "F-7 | \n", + "Islamabad | \n", + "6 | \n", + "For Rent | \n", + "6 | \n", + "22.0 | \n", + "
9999 rows × 8 columns
\n", + "\n", + " | city | \n", + "location | \n", + "Area_in_Marla | \n", + "bedrooms | \n", + "baths | \n", + "
---|---|---|---|---|---|
57800 | \n", + "Karachi | \n", + "Cantt | \n", + "11.4 | \n", + "3 | \n", + "3 | \n", + "
166018 | \n", + "Lahore | \n", + "Green Cap Housing Society | \n", + "3.0 | \n", + "4 | \n", + "4 | \n", + "
150291 | \n", + "Karachi | \n", + "DHA Defence | \n", + "20.0 | \n", + "2 | \n", + "2 | \n", + "
133319 | \n", + "Rawalpindi | \n", + "Bahria Town Rawalpindi | \n", + "5.0 | \n", + "3 | \n", + "4 | \n", + "
119191 | \n", + "Lahore | \n", + "Canal Garden | \n", + "5.0 | \n", + "3 | \n", + "3 | \n", + "
... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "
101191 | \n", + "Rawalpindi | \n", + "Bahria Town Rawalpindi | \n", + "7.0 | \n", + "5 | \n", + "5 | \n", + "
48738 | \n", + "Lahore | \n", + "DHA Defence | \n", + "20.0 | \n", + "5 | \n", + "6 | \n", + "
69691 | \n", + "Karachi | \n", + "Gulshan-e-Iqbal Town | \n", + "12.0 | \n", + "3 | \n", + "3 | \n", + "
160108 | \n", + "Karachi | \n", + "Cantt | \n", + "11.4 | \n", + "3 | \n", + "3 | \n", + "
124749 | \n", + "Islamabad | \n", + "Pakistan Town | \n", + "10.0 | \n", + "3 | \n", + "3 | \n", + "
6999 rows × 5 columns
\n", + "Pipeline(steps=[('columntransformer',\n", + " ColumnTransformer(remainder='passthrough',\n", + " transformers=[('onehotencoder',\n", + " OneHotEncoder(), ['city']),\n", + " ('tfidfvectorizer',\n", + " TfidfVectorizer(max_df=0.5,\n", + " min_df=5,\n", + " ngram_range=(1,\n", + " 3)),\n", + " 'location'),\n", + " ('standardscaler-1',\n", + " StandardScaler(),\n", + " ['Area_in_Marla']),\n", + " ('standardscaler-2',\n", + " StandardScaler(),\n", + " ['bedrooms']),\n", + " ('standardscaler-3',\n", + " StandardScaler(),\n", + " ['baths'])])),\n", + " ('sgdregressor', SGDRegressor(random_state=0))])In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
Pipeline(steps=[('columntransformer',\n", + " ColumnTransformer(remainder='passthrough',\n", + " transformers=[('onehotencoder',\n", + " OneHotEncoder(), ['city']),\n", + " ('tfidfvectorizer',\n", + " TfidfVectorizer(max_df=0.5,\n", + " min_df=5,\n", + " ngram_range=(1,\n", + " 3)),\n", + " 'location'),\n", + " ('standardscaler-1',\n", + " StandardScaler(),\n", + " ['Area_in_Marla']),\n", + " ('standardscaler-2',\n", + " StandardScaler(),\n", + " ['bedrooms']),\n", + " ('standardscaler-3',\n", + " StandardScaler(),\n", + " ['baths'])])),\n", + " ('sgdregressor', SGDRegressor(random_state=0))])
ColumnTransformer(remainder='passthrough',\n", + " transformers=[('onehotencoder', OneHotEncoder(), ['city']),\n", + " ('tfidfvectorizer',\n", + " TfidfVectorizer(max_df=0.5, min_df=5,\n", + " ngram_range=(1, 3)),\n", + " 'location'),\n", + " ('standardscaler-1', StandardScaler(),\n", + " ['Area_in_Marla']),\n", + " ('standardscaler-2', StandardScaler(),\n", + " ['bedrooms']),\n", + " ('standardscaler-3', StandardScaler(),\n", + " ['baths'])])
['city']
OneHotEncoder()
location
TfidfVectorizer(max_df=0.5, min_df=5, ngram_range=(1, 3))
['Area_in_Marla']
StandardScaler()
['bedrooms']
StandardScaler()
['baths']
StandardScaler()
passthrough
SGDRegressor(random_state=0)
Pipeline(steps=[('columntransformer',\n", + " ColumnTransformer(remainder='passthrough',\n", + " transformers=[('onehotencoder',\n", + " OneHotEncoder(), ['city']),\n", + " ('tfidfvectorizer',\n", + " TfidfVectorizer(max_df=0.5,\n", + " min_df=5,\n", + " ngram_range=(1,\n", + " 3)),\n", + " 'location'),\n", + " ('standardscaler-1',\n", + " StandardScaler(),\n", + " ['Area_in_Marla']),\n", + " ('standardscaler-2',\n", + " StandardScaler(),\n", + " ['bedrooms']),\n", + " ('standardscaler-3',\n", + " StandardScaler(),\n", + " ['baths'])])),\n", + " ('sgdregressor',\n", + " SGDRegressor(alpha=1e-05, l1_ratio=0.01, penalty='elasticnet',\n", + " random_state=0))])In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
Pipeline(steps=[('columntransformer',\n", + " ColumnTransformer(remainder='passthrough',\n", + " transformers=[('onehotencoder',\n", + " OneHotEncoder(), ['city']),\n", + " ('tfidfvectorizer',\n", + " TfidfVectorizer(max_df=0.5,\n", + " min_df=5,\n", + " ngram_range=(1,\n", + " 3)),\n", + " 'location'),\n", + " ('standardscaler-1',\n", + " StandardScaler(),\n", + " ['Area_in_Marla']),\n", + " ('standardscaler-2',\n", + " StandardScaler(),\n", + " ['bedrooms']),\n", + " ('standardscaler-3',\n", + " StandardScaler(),\n", + " ['baths'])])),\n", + " ('sgdregressor',\n", + " SGDRegressor(alpha=1e-05, l1_ratio=0.01, penalty='elasticnet',\n", + " random_state=0))])
ColumnTransformer(remainder='passthrough',\n", + " transformers=[('onehotencoder', OneHotEncoder(), ['city']),\n", + " ('tfidfvectorizer',\n", + " TfidfVectorizer(max_df=0.5, min_df=5,\n", + " ngram_range=(1, 3)),\n", + " 'location'),\n", + " ('standardscaler-1', StandardScaler(),\n", + " ['Area_in_Marla']),\n", + " ('standardscaler-2', StandardScaler(),\n", + " ['bedrooms']),\n", + " ('standardscaler-3', StandardScaler(),\n", + " ['baths'])])
['city']
OneHotEncoder()
location
TfidfVectorizer(max_df=0.5, min_df=5, ngram_range=(1, 3))
['Area_in_Marla']
StandardScaler()
['bedrooms']
StandardScaler()
['baths']
StandardScaler()
[]
passthrough
SGDRegressor(alpha=1e-05, l1_ratio=0.01, penalty='elasticnet', random_state=0)