From 982206e93ef80fbc3c577c5c01d1d5655b957aab Mon Sep 17 00:00:00 2001 From: f82c1c4a1227cdba8ff3317d228324d6 Date: Fri, 5 Apr 2024 13:34:10 +0000 Subject: [PATCH] resultc --- module3/exo3/exercice_en.ipynb | 94 +++++++++++++++++++++++----------- 1 file changed, 65 insertions(+), 29 deletions(-) diff --git a/module3/exo3/exercice_en.ipynb b/module3/exo3/exercice_en.ipynb index 6c3e94a..1c05f03 100644 --- a/module3/exo3/exercice_en.ipynb +++ b/module3/exo3/exercice_en.ipynb @@ -176,7 +176,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "From the graph two superimposed phenomena are distinguished, a periodic oscillation superimposed on a slow upward evolution.\n", + "From the graph two superimposed phenomena are distinguished, a periodic oscillation superimposed on a slow upward evolution (slow contribution).\n", "For a better visualization of the periodic oscillation, only the last 300 rows of the table are graphed." ] }, @@ -221,7 +221,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 14, "metadata": {}, "outputs": [ { @@ -255,7 +255,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 23, "metadata": {}, "outputs": [ { @@ -272,15 +272,23 @@ } ], "source": [ - "# Contribution lente. Calculez la valeur moyenne par an et créez une nouvelle colonne 'Concentration moyenne de CO2'\n", + "# Slow contribution\n", + "# Determine the annual average of CO2 concentrations and create a new column 'Mean_CO2_Concentration'\n", "data['Mean_CO2_Concentration'] = data.groupby('Year')['Concentration'].transform('mean')\n", - "# Affichage des premières lignes des données pour vérification\n", + "# Displaying the first rows of data for verification\n", "print(data.head())" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "A graph is made with the average CO2 concentration per year" + ] + }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 29, "metadata": {}, "outputs": [ { @@ -297,7 +305,7 @@ } ], "source": [ - "# Contribution lente. Création du graphique pour montrer la concentration moyenne de CO2 par an au fil du temps\n", + "# Slow contribution. Creating the graph to show the average CO2 concentration per year over time\n", "plt.figure(figsize=(10, 6))\n", "plt.plot(data['Date'], data['Mean_CO2_Concentration'], label='Mean CO2 Concentration per Year Over Time')\n", "plt.title('Mean CO2 Concentration per Year Over Time')\n", @@ -307,9 +315,18 @@ "plt.show()" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "The graph with the average values per year shows horizontal segments for each year which can give the wrong indication that the concentration is constant throughout the year.\n", + "\n", + "To correct this aspect of the graph, a new graph is made but indicating the average CO2 concentration value for the year with a point." + ] + }, { "cell_type": "code", - "execution_count": 37, + "execution_count": 30, "metadata": {}, "outputs": [ { @@ -327,25 +344,32 @@ } ], "source": [ - "# Contribution lente\n", - "# Calcula el promedio anual de concentraciones de CO2\n", + "# Slow contribution\n", + "# Determine the annual average of CO2 concentrations\n", "annual_mean_co2 = data.groupby('Year')['Concentration'].mean()\n", "\n", - "# Renombra la segunda columna\n", + "# Rename the second column\n", "annual_mean_co2 = annual_mean_co2.rename('Mean_CO2_Concentration')\n", "\n", - "# Affichage des premières lignes des données pour vérification\n", + "# Displaying the first rows of data for verification\n", "print(annual_mean_co2.head())" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "A graph is made with points that indicate the average CO2 concentration of the year" + ] + }, { "cell_type": "code", - "execution_count": 38, + "execution_count": 37, "metadata": {}, "outputs": [ { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -357,19 +381,28 @@ } ], "source": [ - "# # Contribution lente. Grafica el promedio anual de concentraciones de CO2\n", + "# Slow contribution. Creating the graph to show the average CO2 concentration per year over time\n", "plt.figure(figsize=(10, 6))\n", - "plt.plot(annual_mean_co2.index, annual_mean_co2.values, marker='o', linestyle='-')\n", - "plt.title('Promedio anual de concentraciones de CO2')\n", - "plt.xlabel('Año')\n", - "plt.ylabel('Concentración de CO2 (ppm)')\n", + "plt.plot(annual_mean_co2.index, annual_mean_co2.values, marker='o', linestyle='-', label='Mean CO2 Concentration per Year Over Time')\n", + "plt.title('Mean CO2 Concentration per Year Over Time')\n", + "plt.xlabel('Year')\n", + "plt.ylabel('CO2 Concentration (ppm)')\n", "plt.grid(True)\n", "plt.show()" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "We now proceed to analyze and determine the periodic oscillation.\n", + "\n", + "For this, a new column \"Oscilation\" is created in the Pandas table with the difference between the original CO2 concentration value and the average value per year calculated in the \"Mean_CO2_Concentration\" column" + ] + }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 32, "metadata": {}, "outputs": [ { @@ -386,15 +419,15 @@ } ], "source": [ - "# Oscillation périodique. Obtencion de la oscilacion et créez une nouvelle colonne 'Oscilation'\n", + "# Periodic oscillation. Obtaining the oscillation and creating a new colony 'Oscillation'\n", "data['Oscilation'] = data['Concentration']-data['Mean_CO2_Concentration']\n", - "# Affichage des premières lignes des données pour vérification\n", + "# Displaying the first rows of data for verification\n", "print(data.head())" ] }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 38, "metadata": {}, "outputs": [ { @@ -411,7 +444,7 @@ } ], "source": [ - "# Oscillation périodique. Création du graphique pour montrer l'oscillation de la concentration de CO2 au fil du temps\n", + "# Periodic oscillation. Creation of the graph to monitor the oscillation of the CO2 concentration over the time\n", "plt.figure(figsize=(10, 6))\n", "plt.plot(data['Date'], data['Oscilation'], label='Oscilation CO2 Concentration Over Time')\n", "plt.title('Oscilation CO2 Concentration Over Time')\n", @@ -423,7 +456,7 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 41, "metadata": {}, "outputs": [ { @@ -440,7 +473,7 @@ } ], "source": [ - "# Oscillation périodique. Création du graphique pour montrer l'oscillation de la concentration de CO2 au fil du temps (300 dernières lignes du tableau)\n", + "# Periodic oscillation. Creation of the graph to monitor the oscillation of the CO2 concentration over the time (last 300 rows of the table)\n", "plt.figure(figsize=(10, 6))\n", "plt.plot(data['Date'][-300:], data['Oscilation'][-300:], label='Oscilation CO2 Concentration Over Time')\n", "plt.title('Oscilation CO2 Concentration Over Time')\n", @@ -454,16 +487,19 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Contribution lente. Pour la contribution lente et ensuite l’extrapolation ultérieure, aucune technique compliquée ne sera appliquée. Nous allons essayer de ajuster une ligne droite. De même, on peut ajuster une ligne droite, une parabole, une exponentielle, puis sélectionner ce qui fonctionne le mieux. Notre premier objectif n'est pas de mettre en œuvre des techniques mathématiques avancées, mais de rédiger un document informatique clair et compréhensible" + "Slow contribution. For the slow contribution and then subsequent extrapolation, no complicated techniques is applied. We try to fit a straight line. Likewise, one can fit a straight line, a parabola, an exponential, and then select what works best. Our first objective is not to implement advanced mathematical techniques, but to write a clear and understandable computer document\n", + "\n", + "Model the slow evolution for extrapolation to 2025" ] }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 42, "metadata": {}, "outputs": [], "source": [ - "# Contribution lente. Modéliser la évolution lente pour extrapolation jusqu’en 2025\n", + "# Slow contribution. Model the slow evolution for extrapolation to 2025\n", + "# Importing the necessary libraries\n", "import numpy as np\n", "from sklearn.linear_model import LinearRegression" ] -- 2.18.1