{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "markdown", "source": [ "Read the data and plot 'lead_time'" ], "metadata": { "id": "GO5gTVYInUxo" } }, { "cell_type": "code", "source": [ "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import pandas as pd\n", "\n", "\n", "data = pd.read_csv('/content/BackOrders.csv')\n", "\n", "# Extract the 'lead_time' feature\n", "lead_time = data['lead_time']\n", "\n", "# Plot the original distribution\n", "plt.hist(lead_time, bins=30, edgecolor='k', alpha=0.7)\n", "plt.title('Original Distribution of Lead Time')\n", "plt.xlabel('Lead Time')\n", "plt.ylabel('Frequency')\n", "plt.show()\n", "\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 983 }, "id": "HeQLoEignPpE", "outputId": "e4c2e735-e929-4a9a-ccb5-acf3354499aa" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ ":6: DtypeWarning: Columns (1,3) have mixed types. Specify dtype option on import or set low_memory=False.\n", " data = pd.read_csv('/content/BackOrders.csv')\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "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\n" }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "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\n" }, "metadata": {} } ] }, { "cell_type": "markdown", "source": [ "**Confidence Intervals**\n", "\n", "Construct and interpret confidence intervals for the mean 'lead_time'.\n", "\n", "Steps:\n", "\n", "1. Sample Data: Select a random sample of 'lead_time' values.\n", "2. Compute the sample mean and standard deviation.\n", "3. Calculate the 95% confidence interval for the mean 'lead_time'.\n", "4. Plot the sample mean and the confidence interval on a graph." ], "metadata": { "id": "QiRFMsesEy3O" } }, { "cell_type": "code", "source": [ "import scipy.stats as stats\n", "\n", "# Draw a random sample\n", "sample = np.random.choice(lead_time, size=30)\n", "\n", "# Calculate mean and standard error\n", "sample_mean = np.mean(sample)\n", "standard_error = stats.sem(sample)\n", "\n", "# Calculate confidence interval\n", "confidence_level = 0.95\n", "confidence_interval = stats.t.interval(confidence_level, len(sample)-1, loc=sample_mean, scale=standard_error)\n", "\n", "print(f\"Sample Mean: {sample_mean}\")\n", "print(f\"95% Confidence Interval: {confidence_interval}\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "MAVBNwB4FIcs", "outputId": "2259dd66-ee63-421c-de59-9f3a3114b449" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Sample Mean: 6.566666666666666\n", "95% Confidence Interval: (5.441380822217193, 7.69195251111614)\n" ] } ] }, { "cell_type": "markdown", "source": [ "**Hypothesis Testing**\n", "\n", "Test whether there is a significant difference in the mean 'lead_time' between products that went on backorder and those that did not.\n", "\n", "Steps:\n", "\n", "1. Formulate Hypotheses:\n", "Null Hypothesis (H0): There is no difference in the mean 'lead_time' between the two groups.\n", "Alternative Hypothesis (H1): There is a difference in the mean 'lead_time' between the two groups.\n", "2. Choose a significance level (e.g., α = 0.05).\n", "3. Use an independent t-test to compare the means of the two groups.\n", "4. Interpret Results: Determine whether to reject or fail to reject the null hypothesis based on the p-value." ], "metadata": { "id": "XRTNzQ2GFeGF" } }, { "cell_type": "code", "source": [ "# Define groups based on the target variable 'went_on_back_order'\n", "group_backorder = data[data['went_on_backorder'] == 'Yes']['lead_time']\n", "group_no_backorder = data[data['went_on_backorder'] == 'No']['lead_time']\n", "\n", "\n", "# Calculate the mean lead time for each group\n", "mean_backorder = np.mean(group_backorder)\n", "mean_no_backorder = np.mean(group_no_backorder)\n", "\n", "# Perform a two-sample t-test\n", "t_statistic, p_value = stats.ttest_ind(group_backorder.dropna(),group_no_backorder.dropna())\n", "\n", "print(f\"Mean Lead Time for Backorder: {mean_backorder}\")\n", "print(f\"Mean Lead Time for No Backorder: {mean_no_backorder}\")\n", "print(f\"T-statistic: {t_statistic}, P-value: {p_value}\")\n", "\n", "if p_value < 0.05:\n", " print(\"The difference in mean lead time is statistically significant.\")\n", "else:\n", " print(\"The difference in mean lead time is not statistically significant.\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "Y3A1GcByFooK", "outputId": "169ce7a8-2039-449c-f044-914d0c35b6ec" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Mean Lead Time for Backorder: 6.322545355091622\n", "Mean Lead Time for No Backorder: 7.847004256941356\n", "T-statistic: -22.224278817834143, P-value: 5.697539588215606e-109\n", "The difference in mean lead time is statistically significant.\n" ] } ] }, { "cell_type": "markdown", "source": [ "**Task:**\n", "\n", "Consider two categorical variables; went_on_backorder and potential_issue. Which test is suitable to determine if there is an association between them or not" ], "metadata": { "id": "rB9Lgc6UPvlY" } }, { "cell_type": "markdown", "source": [ "Steps:\n", "\n", "Formulate Hypotheses:\n", "\n", "1. Null Hypothesis (H0): went_on_back_order and potential_issue are independent (no association).\n", "2. Alternative Hypothesis (H1): There is an association between went_on_back_order and potential_issue.\n", "Create a Contingency Table: Use the two categorical variables to create a contingency table.\n", "\n", "3. Apply the Chi-Square test to evaluate the relationship between these two variables.\n", "\n", "4. Interpret Results: Determine whether to reject or fail to reject the null hypothesis based on the p-value." ], "metadata": { "id": "jijGtQzPUqWy" } }, { "cell_type": "code", "source": [ "# Create a contingency table between 'went_on_backorder' and 'potential_issue'\n", "\n", "\n", "# Perform Chi-Square test of independence\n", "\n", "\n", "if p_val < 0.05:\n", " print(\"Reject the null hypothesis - There is an association between 'went_on_back_order' and 'potential_issue'.\")\n", "else:\n", " print(\"Fail to reject the null hypothesis - No association between 'went_on_back_order' and 'potential_issue'.\")" ], "metadata": { "id": "TC3XNb5tVXUl" }, "execution_count": null, "outputs": [] }, { "cell_type": "markdown", "source": [ "**Task**:\n", "\n", "Compare the variances of two continuous variables, such as national_inv (national inventory level) and lead_time, for products that went on backorder and those that did not." ], "metadata": { "id": "gN1mEtdTWhbR" } }, { "cell_type": "markdown", "source": [ "Steps:\n", "\n", "1.Formulate Hypotheses:\n", "\n", "Null Hypothesis (H0): The variances of national_inv and lead_time for products that went on backorder and those that did not are equal.\n", "Alternative Hypothesis (H1): The variances are not equal.\n", "\n", "2. Separate the data into two groups based on the went_on_back_order column.\n", "\n", "3. Use the ____ test to compare the variances of the two groups.\n", "\n", "4. Use the p-value to determine if the variances differ significantly." ], "metadata": { "id": "jyXoZQQsWpUa" } }, { "cell_type": "code", "source": [ "# Split the data into two groups based on 'went_on_back_order'\n", "\n", "\n", "#converting str and float values in national_inv and lead_time columns to numeric\n", "\n", "\n", "# Calculate variances for 'national_inv' and 'lead_time' for each group\n", "\n", "\n", "# Perform ____ test for both features\n", "\n", "\n", "#Interpret the result\n", "if ________ :\n", " print(\"The variances of 'national_inv' are significantly different between groups.\")\n", " print(\"Reject the null hypothesis.\")\n", "else:\n", " print(\"The variances of 'national_inv' are not significantly different between groups.\")" ], "metadata": { "id": "F_ehRJgEWmb9" }, "execution_count": null, "outputs": [] }, { "cell_type": "markdown", "source": [ "Task:\n", "\n", "Compare the means of a continuous variable, such as lead_time, across multiple categories, like different levels of forecast_3_month, to see if there is a significant difference between the groups.\n", "\n", "Steps:\n", "\n", "1. Formulate Hypotheses:\n", "\n", "Null Hypothesis (H0): The mean lead_time is the same across different levels of forecast_3_month.\n", "Alternative Hypothesis (H1): At least one of the means differs.\n", "2. Group the Data: Split the data based on different levels of forecast_3_month.\n", "\n", "3. Perform _____ analysis to test if there is a significant difference in lead_time across the groups.\n", "\n", "4. Interpret Results: Use the F-statistic and p-value to decide if the means differ significantly.\n", "\n" ], "metadata": { "id": "3uAH_MNiqdkq" } }, { "cell_type": "code", "source": [ "import statsmodels.api as sm\n", "from statsmodels.formula.api import ols\n", "\n", "# Group data by 'forecast_3_month'\n", "\n", "\n", "# Perform _____ analysis\n", "\n", "\n", "# Interpret the results" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "-LLORcN9q1CO", "outputId": "7a59659b-5724-4636-ff4d-3da0da6e7772" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ " sum_sq df F PR(>F)\n", "C(forecast_3_month) 6.338178e+04 1622.0 0.923212 0.986031\n", "Residual 2.394494e+06 56572.0 NaN NaN\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.10/dist-packages/statsmodels/base/model.py:1894: ValueWarning: covariance of constraints does not have full rank. The number of constraints is 1622, but rank is 1613\n", " warnings.warn('covariance of constraints does not have full '\n" ] } ] } ] }