| \n", " | order_id | \n", "customer_id | \n", "restaurant_name | \n", "cuisine_type | \n", "cost_of_the_order | \n", "day_of_the_week | \n", "rating | \n", "food_preparation_time | \n", "delivery_time | \n", "
|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", "1477147 | \n", "337525 | \n", "Hangawi | \n", "Korean | \n", "30.75 | \n", "Weekend | \n", "Not given | \n", "25 | \n", "20 | \n", "
| 1 | \n", "1477685 | \n", "358141 | \n", "Blue Ribbon Sushi Izakaya | \n", "Japanese | \n", "12.08 | \n", "Weekend | \n", "Not given | \n", "25 | \n", "23 | \n", "
| 2 | \n", "1477070 | \n", "66393 | \n", "Cafe Habana | \n", "Mexican | \n", "12.23 | \n", "Weekday | \n", "5 | \n", "23 | \n", "28 | \n", "
| 3 | \n", "1477334 | \n", "106968 | \n", "Blue Ribbon Fried Chicken | \n", "American | \n", "29.20 | \n", "Weekend | \n", "3 | \n", "25 | \n", "15 | \n", "
| 4 | \n", "1478249 | \n", "76942 | \n", "Dirty Bird to Go | \n", "American | \n", "11.59 | \n", "Weekday | \n", "4 | \n", "25 | \n", "24 | \n", "
| \n", " | order_id | \n", "customer_id | \n", "restaurant_name | \n", "cuisine_type | \n", "cost_of_the_order | \n", "day_of_the_week | \n", "rating | \n", "food_preparation_time | \n", "delivery_time | \n", "
|---|---|---|---|---|---|---|---|---|---|
| 1893 | \n", "1476701 | \n", "292602 | \n", "Chipotle Mexican Grill $1.99 Delivery | \n", "Mexican | \n", "22.31 | \n", "Weekend | \n", "5 | \n", "31 | \n", "17 | \n", "
| 1894 | \n", "1477421 | \n", "397537 | \n", "The Smile | \n", "American | \n", "12.18 | \n", "Weekend | \n", "5 | \n", "31 | \n", "19 | \n", "
| 1895 | \n", "1477819 | \n", "35309 | \n", "Blue Ribbon Sushi | \n", "Japanese | \n", "25.22 | \n", "Weekday | \n", "Not given | \n", "31 | \n", "24 | \n", "
| 1896 | \n", "1477513 | \n", "64151 | \n", "Jack's Wife Freda | \n", "Mediterranean | \n", "12.18 | \n", "Weekday | \n", "5 | \n", "23 | \n", "31 | \n", "
| 1897 | \n", "1478056 | \n", "120353 | \n", "Blue Ribbon Sushi | \n", "Japanese | \n", "19.45 | \n", "Weekend | \n", "Not given | \n", "28 | \n", "24 | \n", "
restaurant_name may contain national characters for some records. \n",
"* There are 4 restaurants with non ascii characters in their names.\n",
"* The decimal point in the cost_of_the_order is a dot (.)\n",
"* The raiting column contains both numeric and character values\n",
"* The food_preparation_time and delivery_time are integer, e.g. the time columns were rounded to the nearest minute.\n",
"* There are no duplicate rows in the dataset.\n",
"* The day_of_the_week is represented by group name 'Weekend' or 'Weekday', not by name of the day. In the U.S. weekdays are the 5 days from Monday to Friday, and the weekend are the 2 days, Saturday and Sunday. So, the classes are imbalanced (the ratio of observations in each class are disproportionate) and this might be a problem in future machine learning classification."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "c3kenV4vJY_Q"
},
"source": [
"### **Question 1:** How many rows and columns are present in the data? [0.5 mark]"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Yvz5i-PhJY_Q",
"outputId": "3161deec-04f5-410c-8198-ea111101b9f0"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"There are 1898 rows and 9 columns present in the data.\n"
]
}
],
"source": [
"# Checking the shape of the dataset\n",
"dim = df.shape\n",
"print(f'There are {dim[0]} rows and {dim[1]} columns present in the data.')"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "UsTNy3unJY_R"
},
"source": [
"#### Observations:\n",
"\n",
"The Dataset has 1898 number of rows with 9 columns."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "jRXakVrUJY_R"
},
"source": [
"### **Question 2:** What are the datatypes of the different columns in the dataset? (The info() function can be used) [0.5 mark]"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Kp70Z0BNJY_R",
"outputId": "5bf681ad-6d16-4795-af59-461427cb5c08"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"order_id, customer_id, food_preparation_time, delivery_time\n",
"* 4 columns of object data type: restaurant_name, cuisine_type, day_of_the_week, rating\n",
"* 1 column of float64 datatype: cost_of_the_order\n",
"\n",
"Data type mismatch:\n",
"* day_of_the_week *can only have two values, so it might be converted to boolean datatype*\n",
"* rating *is expected to be a numeric field. We may need to transform the data before converting it to float datatype*"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "pF_92MN6JY_S"
},
"source": [
"### **Question 3:** Are there any missing values in the data? If yes, treat them using an appropriate method. [1 mark]"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Zth-RR1PJY_S",
"outputId": "22975eb2-daf7-4dab-b2d2-27754af6af88"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"order_id 0\n",
"customer_id 0\n",
"restaurant_name 0\n",
"cuisine_type 0\n",
"cost_of_the_order 0\n",
"day_of_the_week 0\n",
"rating 0\n",
"food_preparation_time 0\n",
"delivery_time 0\n",
"dtype: int64"
]
},
"metadata": {},
"execution_count": 8
}
],
"source": [
"# checking missing values\n",
"df.isnull().sum()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "RjlcRQ2GkNK5",
"outputId": "603caa03-1947-4cbb-f655-112b7b2f3a28"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Unique values of day_of_the_week column: ['Weekend' 'Weekday']\n",
"Unique values of rating column: ['Not given' '5' '3' '4']\n",
"rating column. One of the values is 'Not given'. That value could be replaced by NaN and treated appropriatly to convert it to numeric datatype to be able to calculate staticstics. But we added a new column as the original datatype might be useful for vizualization and grouping.\n",
"\n",
"order_id and customer_id are categorical and they type could be changed so that they do not participate in the statistics.\n",
"\n",
"The data in the updated dataset are represented by four different daytatypes:\n",
"* 2 columns of category data type: order_id and customer_id\n",
"* 4 columns of object data type: restaurant_name, cuisine_type, day_of_the_week, rating\n",
"* 2 columns of int64 data type: food_preparation_time and delivery_time\n",
"* 2 column of float64 datatype: cost_of_the_order and frating"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "MnJo7MWrJY_S"
},
"source": [
"### **Question 4:** Check the statistical summary of the data. What is the minimum, average, and maximum time it takes for food to be prepared once an order is placed? [2 marks]"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 300
},
"id": "WprQBgOSJY_T",
"outputId": "107996d5-784c-4fb5-95ac-d5ae8aca6a9b"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" cost_of_the_order food_preparation_time delivery_time frating\n",
"count 1898.000000 1898.000000 1898.000000 1162.000000\n",
"mean 16.498851 27.371970 24.161749 4.344234\n",
"std 7.483812 4.632481 4.972637 0.741478\n",
"min 4.470000 20.000000 15.000000 3.000000\n",
"25% 12.080000 23.000000 20.000000 4.000000\n",
"50% 14.140000 27.000000 25.000000 5.000000\n",
"75% 22.297500 31.000000 28.000000 5.000000\n",
"max 35.410000 35.000000 33.000000 5.000000"
],
"text/html": [
"\n",
" | \n", " | cost_of_the_order | \n", "food_preparation_time | \n", "delivery_time | \n", "frating | \n", "
|---|---|---|---|---|
| count | \n", "1898.000000 | \n", "1898.000000 | \n", "1898.000000 | \n", "1162.000000 | \n", "
| mean | \n", "16.498851 | \n", "27.371970 | \n", "24.161749 | \n", "4.344234 | \n", "
| std | \n", "7.483812 | \n", "4.632481 | \n", "4.972637 | \n", "0.741478 | \n", "
| min | \n", "4.470000 | \n", "20.000000 | \n", "15.000000 | \n", "3.000000 | \n", "
| 25% | \n", "12.080000 | \n", "23.000000 | \n", "20.000000 | \n", "4.000000 | \n", "
| 50% | \n", "14.140000 | \n", "27.000000 | \n", "25.000000 | \n", "5.000000 | \n", "
| 75% | \n", "22.297500 | \n", "31.000000 | \n", "28.000000 | \n", "5.000000 | \n", "
| max | \n", "35.410000 | \n", "35.000000 | \n", "33.000000 | \n", "5.000000 | \n", "
order_id\n",
"* No need to explore order_id as it is unique order key\n",
"\n",
"customer_id\n",
"* There are 1200 unique customers in the dataset.\n",
"* Most of the customers (65%) placed only one order. 22% of the customers placed two orders.\n",
"* Customer 52832 placed 13 orders - more than other customers.\n",
"* Only 33 customers placed five and more orders\n",
"\n",
"restaurant_name\n",
"* There are 178 restaurants in the dataset. 47% of orders were delivered from the most popular ten restaurants.\n",
"* The most popular restaurant by order count is 'Shake Shack' with 219 orders (11.5%)\n",
"\n",
"cuisine_type\n",
"* American is the most popular cuisine (584 orders, ~31%). Japanese and Italian cuisines are on the 2nd and 3rd places of the top.\n",
"* Vietnamese cuisine ends the list as the less popular cuisine with 7 orders (0.4%).\n",
"\n",
"cost_of_the_order\n",
"* Distribution is right-skewed. Median is \\$14.14.\n",
"* It has trimodal distribution. We can assume three categories or three price levels: \\$5-17, \\$20-25, and \\$30-35.\n",
"\n",
"day_of_the_week\n",
"* The dataset represents 71% of orders placed on weekends and 29% on weekdays.\n",
"\n",
"rating\n",
"* Almost 39% of orders were not rated. Among the rated orders the average rating is 4.34. More than half of the rated orders have the maximum rate (5).\n",
"\n",
"food_preparation_time\n",
"* Food preparation time distribution is close to uniform distribution. \n",
"* Food preparation time range is from 20 to 35 mins.\n",
"* Each value of cooking time has an equal probability of 6.25%. Median is 27 minutes, mean ~27 mins.\n",
"* The preparation time seems longer than it should be. The orders for delivery have low priority compared with the in-house orders.\n",
"\n",
"delivery_time\n",
"* Distribution of Delivery time is left-skewed. Median is 25 mins, mean is ~24 mins. \n",
"* Most orders (52%) take 24-30 mins to be delivered, 8% take 31-33 mins, 40% - 15-23 mins."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "K9CqA5H_JY_U"
},
"source": [
"### **Question 7**: Which are the top 5 restaurants in terms of the number of orders received? [1 mark]"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "PaJZ3wlOJY_U",
"outputId": "3858faa9-f40e-42ed-9b26-4e6190ac7a2b"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"The top 5 restaurants in terms of the number of orders received are: ['Shake Shack', 'The Meatball Shop', 'Blue Ribbon Sushi', 'Blue Ribbon Fried Chicken', 'Parm']\n",
"\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"Shake Shack 219\n",
"The Meatball Shop 132\n",
"Blue Ribbon Sushi 119\n",
"Blue Ribbon Fried Chicken 96\n",
"Parm 68\n",
"Name: restaurant_name, dtype: int64"
]
},
"metadata": {},
"execution_count": 15
}
],
"source": [
"print(f'The top 5 restaurants in terms of the number of orders received are: {list(df[\"restaurant_name\"].value_counts()[:5].index)}\\n')\n",
"\n",
"df[\"restaurant_name\"].value_counts()[:5]"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "tnjhWgUfJY_U"
},
"source": [
"#### Observations:\n",
"\n",
"* The top 5 restaurants in terms of the number of orders received are: \n",
" 1. Shake Shack\n",
" 2. The Meatball Shop\n",
" 3. Blue Ribbon Sushi\n",
" 4. Blue Ribbon Fried Chicken\n",
" 5. Parm\n",
"\n",
"* The top 5 restaurants make up 33% of total orders.\n",
"* Shake Shack, the top restaurant had 219 orders (11.5% of total orders)."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "gWPMqGq0JY_U"
},
"source": [
"### **Question 8**: Which is the most popular cuisine on weekends? [1 mark]"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "c-Xnus3VJY_U",
"outputId": "c699d895-e3ba-4437-ffba-2d0d8bd9f005"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"The most popular cuisine on weekends is American\n",
"\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"cuisine_type\n",
"American 0.307180\n",
"Japanese 0.247964\n",
"Italian 0.153220\n",
"Chinese 0.120651\n",
"Mexican 0.039230\n",
"dtype: float64"
]
},
"metadata": {},
"execution_count": 16
}
],
"source": [
"from locale import normalize\n",
"print(f'The most popular cuisine on weekends is {df[df[\"day_of_the_week\"]==\"Weekend\"].value_counts(\"cuisine_type\").index[0]}\\n')\n",
"df[df[\"day_of_the_week\"]==\"Weekend\"].value_counts(\"cuisine_type\", normalize=True)[:5]"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "bpQ270TUJY_U"
},
"source": [
"#### Observations:\n",
"\n",
"* The most popular cuisine on weekends is American. These orders make up 31% of all orders placed on weekends.\n",
"* Weekends are the most popular time to place orders.\n",
"* Cuisine type preferences have weak relationships with the day of the week when orders are placed."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "88xgTqkxJY_U"
},
"source": [
"### **Question 9**: What percentage of the orders cost more than 20 dollars? [2 marks]"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "OTpHyTdzJY_U",
"outputId": "0506e7f7-a9a0-402f-c86b-8a14f7a0754c"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"29.24% of the orders cost more than 20 dollars.\n"
]
}
],
"source": [
"# Percentage of the orders cost more than 20 dollars\n",
"\n",
"print(f'{df[df[\"cost_of_the_order\"]>20].shape[0] / df.shape[0]:.2%} of the orders cost more than 20 dollars.')"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "77KNAC5zJY_U"
},
"source": [
"#### Observations:\n",
"\n",
"29% of the orders cost more than 20 dollars."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "HFyHn7hsJY_V"
},
"source": [
"### **Question 10**: What is the mean order delivery time? [1 mark]"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "cyFL13hNJY_V",
"outputId": "a6fc474a-a159-4b87-f33a-27561988ce58"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"The mean order delivery time is 24.16 mins\n"
]
}
],
"source": [
"# The mean order delivery time\n",
"\n",
"print(f'The mean order delivery time is {df[\"delivery_time\"].mean():.2f} mins')"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "F35SRV-HJY_V"
},
"source": [
"#### Observations:\n",
"\n",
"* The mean order delivery time is about 24 mins. This is slightly lower than the median time (25 mins)\n",
"* Most orders (52%) take 24-30 mins to be delivered, 8% take 31-33 mins, 40% - 15-23 mins"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "48IjaOuDJY_V"
},
"source": [
"### **Question 11:** The company has decided to give 20% discount vouchers to the top 3 most frequent customers. Find the IDs of these customers and the number of orders they placed. [1 mark]"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Hz8-DE4Zge0j",
"outputId": "51af5d32-d895-478e-d87e-08722462a952"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"52832 13\n",
"47440 10\n",
"83287 9\n",
"Name: customer_id, dtype: int64"
]
},
"metadata": {},
"execution_count": 19
}
],
"source": [
"df['customer_id'].value_counts()[:3]"
]
},
{
"cell_type": "code",
"source": [
"print(f\"The 3 most frequent customers contribute {df[df['customer_id'].isin(df['customer_id'].value_counts()[:3].index)]['cost_of_the_order'].sum() / df['cost_of_the_order'].sum():.1%} of total revenue\")\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "47-cAQce0YFB",
"outputId": "90ba1314-ace1-4b82-eac7-a4ad2121c59a"
},
"execution_count": 20,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"The 3 most frequent customers contribute 1.7% of total revenue\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "9tWVwfX6JY_V"
},
"source": [
"#### Observations:\n",
"\n",
"Top-3 customers and the number of orders they placed:\n",
"\n",
"| ID | Orders |\n",
"|-------|--------:|\n",
"| 52832 | 13 |\n",
"| 47440 | 10 |\n",
"| 83287 | 9 |\n",
"\n",
"\n",
"* The three most frequent customers (0.25% of the customer base) contribute 1.7% of total revenue\n",
"* Most of the customers (65%) placed only one order. 22% of the customers placed two orders.\n",
"* Only 33 customers placed five and more orders\n",
"* What is the purpose of the award (vouchers)? The loyalty programs need to be analyzed in more detail."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "AfIc2jPaJY_V"
},
"source": [
"### Multivariate Analysis"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "iqiS0RT_JY_V"
},
"source": [
"### **Question 12**: Perform a multivariate analysis to explore relationships between the important variables in the dataset. (It is a good idea to explore relations between numerical variables as well as relations between numerical and categorical variables) [10 marks]\n"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 581
},
"id": "qzQW_wHZ2kPa",
"outputId": "f017c340-3084-49ff-de20-e55b940745a8"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"| \n", " | restaurant_name | \n", "frating_mean | \n", "frating_count | \n", "
|---|---|---|---|
| 153 | \n", "The Meatball Shop | \n", "4.511905 | \n", "84 | \n", "
| 20 | \n", "Blue Ribbon Fried Chicken | \n", "4.328125 | \n", "64 | \n", "
| 136 | \n", "Shake Shack | \n", "4.278195 | \n", "133 | \n", "
| 21 | \n", "Blue Ribbon Sushi | \n", "4.219178 | \n", "73 | \n", "