diff --git a/03_Grouping/Alcohol_Consumption/Exercise.ipynb b/03_Grouping/Alcohol_Consumption/Exercise.ipynb index d49a518b5..d0c6a72c7 100644 --- a/03_Grouping/Alcohol_Consumption/Exercise.ipynb +++ b/03_Grouping/Alcohol_Consumption/Exercise.ipynb @@ -123,23 +123,23 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 2", + "display_name": "Python 3 (ipykernel)", "language": "python", - "name": "python2" + "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", - "version": 2 + "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", - "pygments_lexer": "ipython2", - "version": "2.7.16" + "pygments_lexer": "ipython3", + "version": "3.12.6" } }, "nbformat": 4, - "nbformat_minor": 0 + "nbformat_minor": 4 } diff --git a/03_Grouping/Alcohol_Consumption/Exercise_with_solutions.ipynb b/03_Grouping/Alcohol_Consumption/Exercise_with_solutions.ipynb index 841a5af59..d2391f475 100644 --- a/03_Grouping/Alcohol_Consumption/Exercise_with_solutions.ipynb +++ b/03_Grouping/Alcohol_Consumption/Exercise_with_solutions.ipynb @@ -25,7 +25,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ @@ -43,7 +43,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "### Step 3. Assign it to a variable called drinks." + "### Step 3. Assign it to a variable called drinks.(Watch the values of Column continent NA (North America), and how Pandas interprets it!" ] }, { @@ -55,6 +55,19 @@ "data": { "text/html": [ "
\n", + "\n", "\n", " \n", " \n", @@ -139,7 +152,7 @@ } ], "source": [ - "drinks = pd.read_csv('https://raw.githubusercontent.com/justmarkham/DAT8/master/data/drinks.csv')\n", + "drinks = pd.read_csv('https://raw.githubusercontent.com/justmarkham/DAT8/master/data/drinks.csv',keep_default_na=False)\n", "drinks.head()" ] }, @@ -152,7 +165,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 5, "metadata": {}, "outputs": [ { @@ -162,12 +175,13 @@ "AF 61.471698\n", "AS 37.045455\n", "EU 193.777778\n", + "NA 145.434783\n", "OC 89.687500\n", "SA 175.083333\n", "Name: beer_servings, dtype: float64" ] }, - "execution_count": 6, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -185,57 +199,134 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 6, "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", + "
countmeanstdmin25%50%75%max
continent
AF53.016.26415138.8464190.01.02.013.00233.0
AS44.09.06818221.6670340.00.01.08.00123.0
EU45.0142.22222297.4217380.059.0128.0195.00370.0
NA23.024.52173928.2663781.05.011.034.00100.0
OC16.035.62500064.5557900.01.08.523.25212.0
SA12.062.41666788.6201891.03.012.098.50221.0
\n", + "
" + ], "text/plain": [ - "continent \n", - "AF count 53.000000\n", - " mean 16.264151\n", - " std 38.846419\n", - " min 0.000000\n", - " 25% 1.000000\n", - " 50% 2.000000\n", - " 75% 13.000000\n", - " max 233.000000\n", - "AS count 44.000000\n", - " mean 9.068182\n", - " std 21.667034\n", - " min 0.000000\n", - " 25% 0.000000\n", - " 50% 1.000000\n", - " 75% 8.000000\n", - " max 123.000000\n", - "EU count 45.000000\n", - " mean 142.222222\n", - " std 97.421738\n", - " min 0.000000\n", - " 25% 59.000000\n", - " 50% 128.000000\n", - " 75% 195.000000\n", - " max 370.000000\n", - "OC count 16.000000\n", - " mean 35.625000\n", - " std 64.555790\n", - " min 0.000000\n", - " 25% 1.000000\n", - " 50% 8.500000\n", - " 75% 23.250000\n", - " max 212.000000\n", - "SA count 12.000000\n", - " mean 62.416667\n", - " std 88.620189\n", - " min 1.000000\n", - " 25% 3.000000\n", - " 50% 12.000000\n", - " 75% 98.500000\n", - " max 221.000000\n", - "dtype: float64" + " count mean std min 25% 50% 75% max\n", + "continent \n", + "AF 53.0 16.264151 38.846419 0.0 1.0 2.0 13.00 233.0\n", + "AS 44.0 9.068182 21.667034 0.0 0.0 1.0 8.00 123.0\n", + "EU 45.0 142.222222 97.421738 0.0 59.0 128.0 195.00 370.0\n", + "NA 23.0 24.521739 28.266378 1.0 5.0 11.0 34.00 100.0\n", + "OC 16.0 35.625000 64.555790 0.0 1.0 8.5 23.25 212.0\n", + "SA 12.0 62.416667 88.620189 1.0 3.0 12.0 98.50 221.0" ] }, - "execution_count": 9, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -253,13 +344,26 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", + "\n", "\n", " \n", " \n", @@ -300,6 +404,13 @@ " \n", " \n", " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", " \n", @@ -323,6 +434,7 @@ "AF 61.471698 16.339623 16.264151 \n", "AS 37.045455 60.840909 9.068182 \n", "EU 193.777778 132.555556 142.222222 \n", + "NA 145.434783 165.739130 24.521739 \n", "OC 89.687500 58.437500 35.625000 \n", "SA 175.083333 114.750000 62.416667 \n", "\n", @@ -331,17 +443,18 @@ "AF 3.007547 \n", "AS 2.170455 \n", "EU 8.617778 \n", + "NA 5.995652 \n", "OC 3.381250 \n", "SA 6.308333 " ] }, - "execution_count": 10, + "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "drinks.groupby('continent').mean()" + "drinks.groupby('continent').mean(numeric_only=True)" ] }, { @@ -353,13 +466,26 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", + "\n", "
8.617778
NA145.434783165.73913024.5217395.995652
OC89.68750058.437500
\n", " \n", " \n", @@ -400,6 +526,13 @@ " \n", " \n", " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", " \n", @@ -423,6 +556,7 @@ "AF 32.0 3.0 2.0 \n", "AS 17.5 16.0 1.0 \n", "EU 219.0 122.0 128.0 \n", + "NA 143.0 137.0 11.0 \n", "OC 52.5 37.0 8.5 \n", "SA 162.5 108.5 12.0 \n", "\n", @@ -431,36 +565,50 @@ "AF 2.30 \n", "AS 1.20 \n", "EU 10.00 \n", + "NA 6.30 \n", "OC 1.75 \n", "SA 6.85 " ] }, - "execution_count": 14, + "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "drinks.groupby('continent').median()" + "drinks.groupby('continent').median(numeric_only=True)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "### Step 8. Print the mean, min and max values for spirit consumption.\n", + "### Step 8. Print the mean, min and max values for spirit consumption for each Continent.\n", "#### This time output a DataFrame" ] }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", + "\n", "
10.00
NA143.0137.011.06.30
OC52.537.0
\n", " \n", " \n", @@ -496,6 +644,12 @@ " \n", " \n", " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", " \n", @@ -517,11 +671,12 @@ "AF 16.339623 0 152\n", "AS 60.840909 0 326\n", "EU 132.555556 0 373\n", + "NA 165.739130 68 438\n", "OC 58.437500 0 254\n", "SA 114.750000 25 302" ] }, - "execution_count": 15, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -529,11 +684,18 @@ "source": [ "drinks.groupby('continent').spirit_servings.agg(['mean', 'min', 'max'])" ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, @@ -547,7 +709,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.3" + "version": "3.12.6" }, "toc": { "base_numbering": 1, @@ -564,5 +726,5 @@ } }, "nbformat": 4, - "nbformat_minor": 1 + "nbformat_minor": 4 } diff --git a/03_Grouping/Alcohol_Consumption/Solutions.ipynb b/03_Grouping/Alcohol_Consumption/Solutions.ipynb index 3783e0b23..61da21c51 100644 --- a/03_Grouping/Alcohol_Consumption/Solutions.ipynb +++ b/03_Grouping/Alcohol_Consumption/Solutions.ipynb @@ -39,7 +39,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "### Step 3. Assign it to a variable called drinks." + "### Step 3. Assign it to a variable called drinks (Watch the values of the Column 'Continent' NA (North America), and how Pandas interprets it!" ] }, { @@ -433,7 +433,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "### Step 8. Print the mean, min and max values for spirit consumption.\n", + "### Step 8. Print the mean, min and max values for spirit consumption by Continent.\n", "#### This time output a DataFrame" ] },
373
NA165.73913068438
OC58.4375000