Diferencias_en_Diferencias.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Diferencias en Diferencias.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyP+SXWrEut0IKpFMSWGAPuD",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/rpasquini/econometria-iae/blob/main/Diferencias_en_Diferencias.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "TqV_-YRrQ__N",
        "outputId": "d0c7ca38-911f-47d2-9204-ed134540df16",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "!pip install geopandas==0.8.1"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: geopandas==0.8.1 in /usr/local/lib/python3.10/dist-packages (0.8.1)\n",
            "Requirement already satisfied: pandas>=0.23.0 in /usr/local/lib/python3.10/dist-packages (from geopandas==0.8.1) (1.5.3)\n",
            "Requirement already satisfied: shapely in /usr/local/lib/python3.10/dist-packages (from geopandas==0.8.1) (2.0.2)\n",
            "Requirement already satisfied: fiona in /usr/local/lib/python3.10/dist-packages (from geopandas==0.8.1) (1.9.5)\n",
            "Requirement already satisfied: pyproj>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from geopandas==0.8.1) (3.6.1)\n",
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.23.0->geopandas==0.8.1) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.23.0->geopandas==0.8.1) (2023.3.post1)\n",
            "Requirement already satisfied: numpy>=1.21.0 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.23.0->geopandas==0.8.1) (1.23.5)\n",
            "Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from pyproj>=2.2.0->geopandas==0.8.1) (2023.7.22)\n",
            "Requirement already satisfied: attrs>=19.2.0 in /usr/local/lib/python3.10/dist-packages (from fiona->geopandas==0.8.1) (23.1.0)\n",
            "Requirement already satisfied: click~=8.0 in /usr/local/lib/python3.10/dist-packages (from fiona->geopandas==0.8.1) (8.1.7)\n",
            "Requirement already satisfied: click-plugins>=1.0 in /usr/local/lib/python3.10/dist-packages (from fiona->geopandas==0.8.1) (1.1.1)\n",
            "Requirement already satisfied: cligj>=0.5 in /usr/local/lib/python3.10/dist-packages (from fiona->geopandas==0.8.1) (0.7.2)\n",
            "Requirement already satisfied: six in /usr/local/lib/python3.10/dist-packages (from fiona->geopandas==0.8.1) (1.16.0)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from fiona->geopandas==0.8.1) (67.7.2)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "xmYfGqZpdQBb"
      },
      "source": [
        "# Investigando efectos del COVID en alquileres usando Diferencias en Diferencias\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pO2zmpgUQ4WH"
      },
      "source": [
        "import geopandas as gpd\n",
        "import numpy as np\n",
        "data=gpd.GeoDataFrame.from_file(\"https://github.com/rpasquini/urban-econometrics/blob/master/data/deptos_amba_0519_0520.zip?raw=true\")\n",
        "df=data.loc[data.l2=='Capital Federal'] # vamos a trabajar con la Capital Federal"
      ],
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CP4vO2XJWmNV",
        "outputId": "16a30f76-880f-4a52-be90-ff299cf21b1d",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "df['airelibre']=np.where((df.patio=='1')| (df.terraza=='1'),1,0)"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/geopandas/geodataframe.py:853: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  super(GeoDataFrame, self).__setitem__(key, value)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "LAutci77gvsl"
      },
      "source": [
        "¿Cuánto fue el alquiler promedio de un departamento tomando el año completo?\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "BbygBdRhgqnQ",
        "outputId": "ea2fcec5-2345-43af-9cbd-4d9d43c55883",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "df.price.mean()"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "25351.83177693887"
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "rpsnXP2_dcly"
      },
      "source": [
        "Exploramos la diferencia en diferencia \\\n",
        "\n",
        "$E[y|t=aire,Post]-E[y|t=aire,Pre]=\\lambda_{POST}+\\beta-\\lambda_{PRE}$\n",
        "$E[y|t=sinaire,Post]-E[y|t=sinaire,Pre]=\\lambda_{POST}-\\lambda_{PRE}$\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "vh7zXzmxdAMT",
        "outputId": "b1e845dd-ba3c-4c51-cba9-3b8ac6ee1f6b",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "dif_airelibre=df.loc[(df.postcovid==1)&(df.airelibre==1)].price.mean()-df.loc[(df.postcovid==0)&(df.airelibre==1)].price.mean()\n",
        "dif_airelibre"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "11670.161339485458"
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "aHWeVX31a7qh",
        "outputId": "06cd24f4-14f8-400d-ae5a-8e42d95ed5fc",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "dif_sin_airelibre=df.loc[(df.postcovid==1)&(df.airelibre==0)].price.mean()-df.loc[(df.postcovid==0)&(df.airelibre==0)].price.mean()\n",
        "dif_sin_airelibre"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "8571.756202733664"
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_m4oUE1QdKOs",
        "outputId": "a6441fb4-ab16-439b-aa4e-d4f2bed502ed",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "dif_airelibre-dif_sin_airelibre"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "3098.405136751793"
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "CbqeUGhDfX-d"
      },
      "source": [
        "Misma cuenta en logs"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "MEB01AYhfc3G",
        "outputId": "5ea5bbd7-b00d-4894-ded5-241b3d7038c3",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "df['logprice']=np.log(df.price)\n",
        "df['logpricem2']=np.log(df.price/df.surface_to)"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/geopandas/geodataframe.py:853: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  super(GeoDataFrame, self).__setitem__(key, value)\n",
            "/usr/local/lib/python3.10/dist-packages/geopandas/geodataframe.py:853: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  super(GeoDataFrame, self).__setitem__(key, value)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "EMIUtWRogKIm",
        "outputId": "10b828cd-ac00-44d0-e274-b973188e7bce",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "dif_airelibre=df.loc[(df.postcovid==1)&(df.airelibre==1)].logprice.mean()-df.loc[(df.postcovid==0)&(df.airelibre==1)].logprice.mean()\n",
        "dif_sin_airelibre=df.loc[(df.postcovid==1)&(df.airelibre==0)].logprice.mean()-df.loc[(df.postcovid==0)&(df.airelibre==0)].logprice.mean()\n",
        "dif_airelibre-dif_sin_airelibre"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.017190559076800227"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Wfm3nFcfhKlc"
      },
      "source": [
        "# Utilizando Regresión\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "T6fX9nnuhkvI",
        "outputId": "ea7131b8-871e-4222-ad2d-17c71752b97f",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "df['DD']=df.postcovid*df.airelibre"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/geopandas/geodataframe.py:853: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  super(GeoDataFrame, self).__setitem__(key, value)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "9bRM2eqOhN9p"
      },
      "source": [
        "import statsmodels.api as sm\n",
        "def regress(lista, data):\n",
        "    \"\"\"\n",
        "    Funcion que realiza la regresion OLS\n",
        "    La primera variable de la lista es la dependiente, el resto son las explicativas\n",
        "    data es la base de datos\n",
        "    \"\"\"\n",
        "    datos=data[lista]\n",
        "    # el metodo dropna() me permite eliminar las filas que tienen algun valor missing\n",
        "    datos=datos.dropna()\n",
        "    Y=datos[lista[0]]\n",
        "    X=datos[lista[1:]]\n",
        "    X=sm.add_constant(X)\n",
        "    modelo=sm.OLS(Y,X)\n",
        "    resultados=modelo.fit()\n",
        "    print(resultados.summary())"
      ],
      "execution_count": 11,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "gw-iVvJNhZ8X",
        "outputId": "2c2e53d6-0449-4db5-b34f-1b027912d64b",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "regress(['logprice','postcovid','airelibre','DD'],data=df)"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "                            OLS Regression Results                            \n",
            "==============================================================================\n",
            "Dep. Variable:               logprice   R-squared:                       0.038\n",
            "Model:                            OLS   Adj. R-squared:                  0.037\n",
            "Method:                 Least Squares   F-statistic:                     196.4\n",
            "Date:                Mon, 20 Nov 2023   Prob (F-statistic):          5.75e-125\n",
            "Time:                        15:48:52   Log-Likelihood:                -10897.\n",
            "No. Observations:               15099   AIC:                         2.180e+04\n",
            "Df Residuals:                   15095   BIC:                         2.183e+04\n",
            "Df Model:                           3                                         \n",
            "Covariance Type:            nonrobust                                         \n",
            "==============================================================================\n",
            "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
            "------------------------------------------------------------------------------\n",
            "const          9.9326      0.005   2087.057      0.000       9.923       9.942\n",
            "postcovid      0.2837      0.017     16.257      0.000       0.249       0.318\n",
            "airelibre      0.1436      0.010     13.951      0.000       0.123       0.164\n",
            "DD             0.0172      0.035      0.486      0.627      -0.052       0.086\n",
            "==============================================================================\n",
            "Omnibus:                     2254.328   Durbin-Watson:                   1.527\n",
            "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             3676.706\n",
            "Skew:                           1.018   Prob(JB):                         0.00\n",
            "Kurtosis:                       4.305   Cond. No.                         9.34\n",
            "==============================================================================\n",
            "\n",
            "Notes:\n",
            "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "iq2uTg3ZiGHy",
        "outputId": "4e39d4b8-d6f5-4d38-bdca-9644183bc1d8",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "regress(['price','postcovid','airelibre','DD'],data=df)"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "                            OLS Regression Results                            \n",
            "==============================================================================\n",
            "Dep. Variable:                  price   R-squared:                       0.029\n",
            "Model:                            OLS   Adj. R-squared:                  0.029\n",
            "Method:                 Least Squares   F-statistic:                     151.1\n",
            "Date:                Mon, 20 Nov 2023   Prob (F-statistic):           1.75e-96\n",
            "Time:                        15:48:52   Log-Likelihood:            -1.6955e+05\n",
            "No. Observations:               15099   AIC:                         3.391e+05\n",
            "Df Residuals:                   15095   BIC:                         3.391e+05\n",
            "Df Model:                           3                                         \n",
            "Covariance Type:            nonrobust                                         \n",
            "==============================================================================\n",
            "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
            "------------------------------------------------------------------------------\n",
            "const       2.371e+04    174.158    136.150      0.000    2.34e+04    2.41e+04\n",
            "postcovid   8571.7562    638.577     13.423      0.000    7320.068    9823.444\n",
            "airelibre   4241.3780    376.554     11.264      0.000    3503.287    4979.469\n",
            "DD          3098.4051   1293.275      2.396      0.017     563.430    5633.380\n",
            "==============================================================================\n",
            "Omnibus:                    11414.989   Durbin-Watson:                   1.624\n",
            "Prob(Omnibus):                  0.000   Jarque-Bera (JB):           234514.338\n",
            "Skew:                           3.520   Prob(JB):                         0.00\n",
            "Kurtosis:                      20.978   Cond. No.                         9.34\n",
            "==============================================================================\n",
            "\n",
            "Notes:\n",
            "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "U0gh-cKw_NIA",
        "outputId": "cfbded72-16ce-4008-b761-3131df94c8e7",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "df.start_date"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0        2019-07-28\n",
              "1        2019-07-28\n",
              "2        2019-07-28\n",
              "3        2019-07-28\n",
              "4        2019-07-28\n",
              "            ...    \n",
              "23130    2019-07-31\n",
              "23131    2019-07-31\n",
              "23132    2019-07-31\n",
              "23133    2019-07-31\n",
              "23134    2019-07-31\n",
              "Name: start_date, Length: 15099, dtype: object"
            ]
          },
          "metadata": {},
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "xSAVX3VfEXag"
      },
      "source": [
        "# Inspección gráfica del cumplimiento del supuesto de tendencias comunes\n",
        "\n",
        "Vamos a mirar los promedios mensuales y por trimetre. Para eso voy a extraer de la fecha el mes-anio y el trimestre-anio correspondiente.\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "kys8h-9I-yir",
        "outputId": "ea072804-5915-45af-f1a3-ca5689fc8604",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "import pandas as pd\n",
        "df['monthyear']=pd.to_datetime(df.start_date).dt.to_period('M')"
      ],
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/geopandas/geodataframe.py:853: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  super(GeoDataFrame, self).__setitem__(key, value)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ceo4uqgWAWLV",
        "outputId": "84f8f97e-1a5f-4076-dbc2-1696af4929c4",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 483
        }
      },
      "source": [
        "df_months=df.groupby(by=['monthyear','airelibre']).logprice.mean().rename('media').reset_index()\n",
        "ax=df_months.loc[df_months.airelibre==0].plot(x='monthyear',y='media', label='Sin aire libre')\n",
        "df_months.loc[df_months.airelibre==1].plot(x='monthyear',y='media', ax=ax, label='Aire libre')"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<Axes: xlabel='monthyear'>"
            ]
          },
          "metadata": {},
          "execution_count": 16
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_giZTAc9DmA9",
        "outputId": "cc5a06aa-a3ee-446a-a43c-ccadb01e692a",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 588
        }
      },
      "source": [
        "df['quarteryear']=pd.to_datetime(df.start_date).dt.to_period('Q')\n",
        "df_quarters=df.groupby(by=['quarteryear','airelibre']).logprice.mean().rename('media').reset_index()\n",
        "ax=df_quarters.loc[df_quarters.airelibre==0].plot(x='quarteryear',y='media', label='Sin aire libre')\n",
        "df_quarters.loc[df_quarters.airelibre==1].plot(x='quarteryear',y='media', ax=ax, label='Aire libre')"
      ],
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/geopandas/geodataframe.py:853: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  super(GeoDataFrame, self).__setitem__(key, value)\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<Axes: xlabel='quarteryear'>"
            ]
          },
          "metadata": {},
          "execution_count": 17
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    }
  ]
}