{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "DtNBZFHO3M7n" }, "source": [ "# **Waze Project**\n", "**Course 3 - The Power of Statistics**" ] }, { "cell_type": "markdown", "metadata": { "id": "WVeXS7BNzX6e" }, "source": [ "Your team is nearing the midpoint of their user churn project. So far, you’ve completed a project proposal, and used Python to explore and analyze Waze’s user data. You’ve also used Python to create data visualizations. The next step is to use statistical methods to analyze and interpret your data.\n", "\n", "You receive a new email from Sylvester Esperanza, your project manager. Sylvester tells your team about a new request from leadership: to analyze the relationship between mean amount of rides and device type. You also discover follow-up emails from three other team members: May Santner, Chidi Ga, and Harriet Hadzic. These emails discuss the details of the analysis. They would like a statistical analysis of ride data based on device type. In particular, leadership wants to know if there is a statistically significant difference in mean amount of rides between iPhone® users and Android™ users. A final email from Chidi includes your specific assignment: to conduct a two-sample hypothesis test (t-test) to analyze the difference in the mean amount of rides between iPhone users and Android users.\n", "\n", "A notebook was structured and prepared to help you in this project. Please complete the following questions and prepare an executive summary." ] }, { "cell_type": "markdown", "metadata": { "id": "rgSbVJvomcVa" }, "source": [ "# **Course 3 End-of-course project: Data exploration and hypothesis testing**\n", "\n", "In this activity, you will explore the data provided and conduct a hypothesis test.\n", "
\n", "\n", "**The purpose** of this project is to demonstrate knowledge of how to conduct a two-sample hypothesis test.\n", "\n", "**The goal** is to apply descriptive statistics and hypothesis testing in Python.\n", "
\n", "\n", "*This activity has three parts:*\n", "\n", "**Part 1:** Imports and data loading\n", "* What data packages will be necessary for hypothesis testing?\n", "\n", "**Part 2:** Conduct hypothesis testing\n", "* How did computing descriptive statistics help you analyze your data?\n", "\n", "* How did you formulate your null hypothesis and alternative hypothesis?\n", "\n", "**Part 3:** Communicate insights with stakeholders\n", "\n", "* What key business insight(s) emerged from your hypothesis test?\n", "\n", "* What business recommendations do you propose based on your results?\n", "\n", "
\n", "\n", "\n", "Follow the instructions and answer the questions below to complete the activity. Then, you will complete an Executive Summary using the questions listed on the PACE Strategy Document.\n", "\n", "Be sure to complete this activity before moving on. The next course item will provide you with a completed exemplar to compare to your own work.\n" ] }, { "cell_type": "markdown", "metadata": { "id": "9GHVSxqehVpv" }, "source": [ "# **Data exploration and hypothesis testing**" ] }, { "cell_type": "markdown", "metadata": { "id": "N8qrn_UAzX6j" }, "source": [ "\n", "\n", "# **PACE stages**\n" ] }, { "cell_type": "markdown", "metadata": { "id": "WQ1oMthKhfzP" }, "source": [ "Throughout these project notebooks, you'll see references to the problem-solving framework PACE. The following notebook components are labeled with the respective PACE stage: Plan, Analyze, Construct, and Execute." ] }, { "cell_type": "markdown", "metadata": { "id": "Bb1HNu3FzX6k" }, "source": [ "\n", "\n", "\n", "## **PACE: Plan**\n", "\n", "Consider the questions in your PACE Strategy Document and those below to craft your response:\n", "1. What is your research question for this data project? Later on, you will need to formulate the null and alternative hypotheses as the first step of your hypothesis test. Consider your research question now, at the start of this task.\n" ] }, { "cell_type": "markdown", "metadata": { "id": "F6_h60RuXQIz" }, "source": [ "To determine if there is a statistically significant difference in mean amount of rides between iPhone® users and Android™ users." ] }, { "cell_type": "markdown", "metadata": { "id": "Kp3uDhhSg_qu" }, "source": [ "*Complete the following tasks to perform statistical analysis of your data:*" ] }, { "cell_type": "markdown", "metadata": { "id": "xgQEdIN7f1Jq" }, "source": [ "### **Task 1. Imports and data loading**\n", "\n", "\n" ] }, { "cell_type": "markdown", "metadata": { "id": "ehehvUzFj0-e" }, "source": [ "Import packages and libraries needed to compute descriptive statistics and conduct a hypothesis test." ] }, { "cell_type": "markdown", "metadata": { "id": "e6cryW4WgiIL" }, "source": [ "
\n", "

Hint:

\n", "\n", "Before you begin, recall the following Python packages and functions:\n", "\n", "*Main functions*: stats.ttest_ind(a, b, equal_var)\n", "\n", "*Other functions*: mean()\n", "\n", "*Packages*: pandas, stats.scipy\n", "\n", "
" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "id": "1Q-GL2UrgWWG" }, "outputs": [], "source": [ "# Import any relevant packages or libraries\n", "import pandas as pd\n", "import numpy as np\n", "from scipy import stats" ] }, { "cell_type": "markdown", "metadata": { "id": "stMe9uT3kOmF" }, "source": [ "Import the dataset.\n", "\n", "**Note:** As shown in this cell, the dataset has been automatically loaded in for you. You do not need to download the .csv file, or provide more code, in order to access the dataset and proceed with this lab. Please continue with this activity by completing the following instructions." ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "id": "2qAt6Upaeg6U" }, "outputs": [], "source": [ "# Load dataset into dataframe\n", "df = pd.read_csv('waze_dataset.csv')" ] }, { "cell_type": "markdown", "metadata": { "id": "c8paWsdKzX6o" }, "source": [ "\n", "\n", "\n", "\n", "## **PACE: Analyze and Construct**\n", "\n", "Consider the questions in your PACE Strategy Document and those below to craft your response:\n", "1. Data professionals use descriptive statistics for exploratory data analysis (EDA). How can computing descriptive statistics help you learn more about your data in this stage of your analysis?\n" ] }, { "cell_type": "markdown", "metadata": { "id": "rX5xJnWUXxsW" }, "source": [ "Descriptive statistics are used to explore and summarize data." ] }, { "cell_type": "markdown", "metadata": { "id": "UKhYTdVhf5B2" }, "source": [ "### **Task 2. Data exploration**\n", "\n", "Use descriptive statistics to conduct exploratory data analysis (EDA)." ] }, { "cell_type": "markdown", "metadata": { "id": "AzYm91yQrS9s" }, "source": [ "
\n", "

Hint:

\n", "\n", "Refer back to *Self Review Descriptive Statistics* for this step-by-step proccess.\n", "\n", "
" ] }, { "cell_type": "markdown", "metadata": { "id": "JAq7ag0pTNgl" }, "source": [ "**Note:** In the dataset, `device` is a categorical variable with the labels `iPhone` and `Android`.\n", "\n", "In order to perform this analysis, you must turn each label into an integer. The following code assigns a `1` for an `iPhone` user and a `2` for `Android`. It assigns this label back to the variable `device_new`.\n", "\n", "**Note:** Creating a new variable is ideal so that you don't overwrite original data.\n", "\n" ] }, { "cell_type": "markdown", "metadata": { "id": "GaJ4golwD8et" }, "source": [ "1. Create a dictionary called `map_dictionary` that contains the class labels (`'Android'` and `'iPhone'`) for keys and the values you want to convert them to (`2` and `1`) as values.\n", "\n", "2. Create a new column called `device_type` that is a copy of the `device` column.\n", "\n", "3. Use the [`map()`](https://pandas.pydata.org/docs/reference/api/pandas.Series.map.html#pandas-series-map) method on the `device_type` series. Pass `map_dictionary` as its argument. Reassign the result back to the `device_type` series.\n", "

\n", "When you pass a dictionary to the `Series.map()` method, it will replace the data in the series where that data matches the dictionary's keys. The values that get imputed are the values of the dictionary.\n", "\n", "```\n", "Example:\n", "df['column']\n", "```\n", "\n", "|column |\n", "| :-: |\n", "| A |\n", "| B |\n", "| A |\n", "| B |\n", "\n", "```\n", "map_dictionary = {'A': 2, 'B': 1}\n", "df['column'] = df['column'].map(map_dictionary)\n", "df['column']\n", "```\n", "\n", "|column |\n", "| :-: |\n", "| 2 |\n", "| 1 |\n", "| 2 |\n", "| 1 |\n" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
IDlabelsessionsdrivestotal_sessionsn_days_after_onboardingtotal_navigations_fav1total_navigations_fav2driven_km_drivesduration_minutes_drivesactivity_daysdriving_daysdevicedevice_type
count14999.0000001429914999.00000014999.00000014999.00000014999.00000014999.00000014999.00000014999.00000014999.00000014999.00000014999.0000001499914999.000000
uniqueNaN2NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN2NaN
topNaNretainedNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNiPhoneNaN
freqNaN11763NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN9672NaN
mean7499.000000NaN80.63377667.281152189.9644471749.837789121.60597429.6725124039.3409211860.97601215.53710212.179879NaN1.355157
std4329.982679NaN80.69906565.913872136.4051281008.513876148.12154445.3946512502.1493341446.7022889.0046557.824036NaN0.478577
min0.000000NaN0.0000000.0000000.2202114.0000000.0000000.00000060.44125018.2820820.0000000.000000NaN1.000000
25%3749.500000NaN23.00000020.00000090.661156878.0000009.0000000.0000002212.600607835.9962608.0000005.000000NaN1.000000
50%7499.000000NaN56.00000048.000000159.5681151741.00000071.0000009.0000003493.8580851478.24985916.00000012.000000NaN1.000000
75%11248.500000NaN112.00000093.000000254.1923412623.500000178.00000043.0000005289.8612622464.36263223.00000019.000000NaN2.000000
max14998.000000NaN743.000000596.0000001216.1546333500.0000001236.000000415.00000021183.40189015851.72716031.00000030.000000NaN2.000000
\n", "
" ], "text/plain": [ " ID label sessions drives total_sessions \\\n", "count 14999.000000 14299 14999.000000 14999.000000 14999.000000 \n", "unique NaN 2 NaN NaN NaN \n", "top NaN retained NaN NaN NaN \n", "freq NaN 11763 NaN NaN NaN \n", "mean 7499.000000 NaN 80.633776 67.281152 189.964447 \n", "std 4329.982679 NaN 80.699065 65.913872 136.405128 \n", "min 0.000000 NaN 0.000000 0.000000 0.220211 \n", "25% 3749.500000 NaN 23.000000 20.000000 90.661156 \n", "50% 7499.000000 NaN 56.000000 48.000000 159.568115 \n", "75% 11248.500000 NaN 112.000000 93.000000 254.192341 \n", "max 14998.000000 NaN 743.000000 596.000000 1216.154633 \n", "\n", " n_days_after_onboarding total_navigations_fav1 \\\n", "count 14999.000000 14999.000000 \n", "unique NaN NaN \n", "top NaN NaN \n", "freq NaN NaN \n", "mean 1749.837789 121.605974 \n", "std 1008.513876 148.121544 \n", "min 4.000000 0.000000 \n", "25% 878.000000 9.000000 \n", "50% 1741.000000 71.000000 \n", "75% 2623.500000 178.000000 \n", "max 3500.000000 1236.000000 \n", "\n", " total_navigations_fav2 driven_km_drives duration_minutes_drives \\\n", "count 14999.000000 14999.000000 14999.000000 \n", "unique NaN NaN NaN \n", "top NaN NaN NaN \n", "freq NaN NaN NaN \n", "mean 29.672512 4039.340921 1860.976012 \n", "std 45.394651 2502.149334 1446.702288 \n", "min 0.000000 60.441250 18.282082 \n", "25% 0.000000 2212.600607 835.996260 \n", "50% 9.000000 3493.858085 1478.249859 \n", "75% 43.000000 5289.861262 2464.362632 \n", "max 415.000000 21183.401890 15851.727160 \n", "\n", " activity_days driving_days device device_type \n", "count 14999.000000 14999.000000 14999 14999.000000 \n", "unique NaN NaN 2 NaN \n", "top NaN NaN iPhone NaN \n", "freq NaN NaN 9672 NaN \n", "mean 15.537102 12.179879 NaN 1.355157 \n", "std 9.004655 7.824036 NaN 0.478577 \n", "min 0.000000 0.000000 NaN 1.000000 \n", "25% 8.000000 5.000000 NaN 1.000000 \n", "50% 16.000000 12.000000 NaN 1.000000 \n", "75% 23.000000 19.000000 NaN 2.000000 \n", "max 31.000000 30.000000 NaN 2.000000 " ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.describe(include=\"all\")" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "id": "piHSZbnjEXw-" }, "outputs": [ { "data": { "text/plain": [ "0 2\n", "1 1\n", "2 2\n", "3 1\n", "4 2\n", "Name: device_type, dtype: int64" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 1. Create `map_dictionary`\n", "map_dictionary = {'Android': 2, 'iPhone': 1}\n", "# 2. Create new `device_type` column\n", "df['device_type'] = df['device'].copy()\n", "# 3. Map the new column to the dictionary\n", "df['device_type'] = df['device_type'].map(map_dictionary)\n", "df['device_type'].head()" ] }, { "cell_type": "markdown", "metadata": { "id": "-fFiNg4hdGBK" }, "source": [ "You are interested in the relationship between device type and the number of drives. One approach is to look at the average number of drives for each device type. Calculate these averages." ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "id": "2LGEWrdVXgI2" }, "outputs": [ { "data": { "text/plain": [ "device_type\n", "1 67.859078\n", "2 66.231838\n", "Name: drives, dtype: float64" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.groupby(\"device_type\")[\"drives\"].mean()" ] }, { "cell_type": "markdown", "metadata": { "id": "Z_u-zWvGdfII" }, "source": [ "Based on the averages shown, it appears that drivers who use an iPhone device to interact with the application have a higher number of drives on average. However, this difference might arise from random sampling, rather than being a true difference in the number of drives. To assess whether the difference is statistically significant, you can conduct a hypothesis test." ] }, { "cell_type": "markdown", "metadata": { "id": "QpFRQDaNzX6p" }, "source": [ "\n", "### **Task 3. Hypothesis testing**\n", "\n", "Your goal is to conduct a two-sample t-test. Recall the steps for conducting a hypothesis test:\n", "\n", "\n", "1. State the null hypothesis and the alternative hypothesis\n", "2. Choose a signficance level\n", "3. Find the p-value\n", "4. Reject or fail to reject the null hypothesis\n", "\n", "**Note:** This is a t-test for two independent samples. This is the appropriate test since the two groups are independent (Android users vs. iPhone users)." ] }, { "cell_type": "markdown", "metadata": { "id": "phXxr74vVPrs" }, "source": [ "Recall the difference between the null hypothesis ($H_0$) and the alternative hypothesis ($H_A$).\n", "\n", "**Question:** What are your hypotheses for this data project?" ] }, { "cell_type": "markdown", "metadata": { "id": "SkDeGggZYM84" }, "source": [ "$H_0$: There is no difference in the mean amount of rides between iPhone® users and Android™ users.\n", "\n", "$H_A$: There is a difference in the mean amount of rides between iPhone® users and Android™ users." ] }, { "cell_type": "markdown", "metadata": { "id": "IVHpnfvNeTUA" }, "source": [ "Next, choose 5% as the significance level and proceed with a two-sample t-test.\n", "\n", "You can use the `stats.ttest_ind()` function to perform the test.\n", "\n", "\n", "**Technical note**: The default for the argument `equal_var` in `stats.ttest_ind()` is `True`, which assumes population variances are equal. This equal variance assumption might not hold in practice (that is, there is no strong reason to assume that the two groups have the same variance); you can relax this assumption by setting `equal_var` to `False`, and `stats.ttest_ind()` will perform the unequal variances $t$-test (known as Welch's `t`-test). Refer to the [scipy t-test documentation](https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.ttest_ind.html) for more information.\n", "\n", "\n", "1. Isolate the `drives` column for iPhone users.\n", "2. Isolate the `drives` column for Android users.\n", "3. Perform the t-test" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "id": "rdlsXg7Dhbrd" }, "outputs": [ { "data": { "text/plain": [ "Ttest_indResult(statistic=1.4635232068852353, pvalue=0.1433519726802059)" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 1. Isolate the `drives` column for iPhone users.\n", "a = df[df[\"device_type\"] == 1][\"drives\"]\n", "# 2. Isolate the `drives` column for Android users.\n", "b = df[df[\"device_type\"] == 2][\"drives\"]\n", "# 3. Perform the t-test\n", "stats.ttest_ind(a=a, b=b, equal_var=False)" ] }, { "cell_type": "markdown", "metadata": { "id": "64Wq_VSaVsNm" }, "source": [ "**Question:** Based on the p-value you got above, do you reject or fail to reject the null hypothesis?" ] }, { "cell_type": "markdown", "metadata": { "id": "SGLHv2FY1P2-" }, "source": [ "With a p-value (0.1434) being higher than 0.05 (as the significance level is 5%), we fail to reject the null hypothesis.\n", "\n", "Therefore, we can conclude at the 5% significance level that there is no statistically significant difference in the mean amount of rides between iPhone® users and Android™ users." ] }, { "cell_type": "markdown", "metadata": { "id": "Ab4e-W3mzX6r" }, "source": [ "\n", "\n", "## **PACE: Execute**\n", "\n", "Consider the questions in your PACE Strategy Document to reflect on the Execute stage." ] }, { "cell_type": "markdown", "metadata": { "id": "h1PRfiD3hcwE" }, "source": [ "### **Task 4. Communicate insights with stakeholders**" ] }, { "cell_type": "markdown", "metadata": { "id": "ItreFaZKhvVw" }, "source": [ "Now that you've completed your hypothesis test, the next step is to share your findings with the Waze leadership team. Consider the following question as you prepare to write your executive summary:\n", "\n", "* What business insight(s) can you draw from the result of your hypothesis test?" ] }, { "cell_type": "markdown", "metadata": { "id": "-CgNingVY4Bw" }, "source": [ "We can conclude at the 5% significance level that there is no difference in the mean amount of rides between iPhone users and Android users of Waze.
\n", "One possible next step is to explore what other factors influence the variation in the number of drives, and run additional hypothesis tests to learn more about user behavior. Further, temporary changes in marketing or user interface for the Waze app may provide more data to investigate churn." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Congratulations!** You've completed this lab. However, you may not notice a green check mark next to this item on Coursera's platform. Please continue your progress regardless of the check mark. Just click on the \"save\" icon at the top of this notebook to ensure your work has been logged." ] } ], "metadata": { "colab": { "provenance": [ { "file_id": "1VMShPM3amGvcOZx0J5yHz1kb04rzCFvN", "timestamp": 1671052168408 }, { "file_id": "1su07KaK4RI6MI85tMf2H19qop9LcqqDy", "timestamp": 1669648371757 }, { "file_id": "1f5FzGbEQi1DvhHY8u-K32sklfpgir_pK", "timestamp": 1669589913543 } ] }, "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": 1 }