diff --git a/.ipynb_checkpoints/Untitled-checkpoint.ipynb b/.ipynb_checkpoints/Untitled-checkpoint.ipynb index 7b5f0b3..a14e344 100644 --- a/.ipynb_checkpoints/Untitled-checkpoint.ipynb +++ b/.ipynb_checkpoints/Untitled-checkpoint.ipynb @@ -41,20 +41,100 @@ ] }, { - "cell_type": "code", - "execution_count": null, - "id": "f56d81a7", + "cell_type": "markdown", + "id": "8711159a", "metadata": {}, - "outputs": [], - "source": [] + "source": [ + "### Steps to follow\n", + "\n", + "1. Define the null hypothesis: \n", + "'The means are similar. Changing the power of the plasma beam does NOT have significant change on etching rate by the machine'\n", + "\n", + "2. Define the alternative hypothesis: \n", + "'The means are different. Changing the power of the plasma beam DO have significant change on etching rate by the machine'\n", + "\n", + "3. Level of significent:\n", + "0.05 ( 95% )\n", + "\n", + "4. Degrees of freedom of model, error terms, and total DoF\n", + "4.1 Degrees of freedom (rows - 1) * (columns - 1) --> (15 - 1) * (2 - 1) = 14\n", + "\n", + "4.2 Error terms\n", + "\n", + "4.3 Total DoF\n", + "\n", + "\n", + "\n" + ] }, { - "cell_type": "code", - "execution_count": null, - "id": "a891a030", + "cell_type": "markdown", + "id": "f4ee91dd", "metadata": {}, - "outputs": [], - "source": [] + "source": [ + "### Calculation of F ratio (F statistics)\n", + "\n", + "\n", + "\n", + "#### Groups\t\t\t\n", + "- 160w:\t5\t\t\n", + "- 180w:\t5\t\t\n", + "- 200w:\t5\t\t\n", + "\t\t\t\n", + "#### How to calculate f ratio\n", + "\n", + "1) Cx:\tTotal of etching rate *2 / data points\t--> 690.0685067\n", + "\n", + "2) SSt: Total of square - Cx\t-->\t21.13389333\n", + "\n", + "3) Ssa: SUM(Total score of square in each group / group number (K)) - Cx\t\t\n", + "\t160w\t167.73632\t\n", + "\t180w\t194.56322\t\n", + "\t200w\t345.94562\t\n", + "\tSUM\t708.24516\t\n", + " \n", + "4) SSa= (SUM - Cx) = 18.17665333\n", + "\n", + "5) SSw:\tSSt - Ssa\t=\t2.95724\n", + "\n", + "6) MSSa:\tSSa/(k-1)\t=\t9.088326667\n", + "\n", + "7) MSSw:\tSSw/(n-k)\t=\t0.246436667\n", + "\n", + "8) f ratio:\tMSSa/MSSw\t=\t36.8789547" + ] + }, + { + "cell_type": "markdown", + "id": "9b68ddbe", + "metadata": {}, + "source": [ + "### Check the f table\n", + "- DoF1 = K - 1 = 3 - 1 = 2\n", + "- DoF2 = n - K = 15 - 3 = 12\n", + "\n", + "\n", + "F score = 3.885" + ] + }, + { + "cell_type": "markdown", + "id": "30bea853", + "metadata": {}, + "source": [ + "### Results" + ] + }, + { + "cell_type": "markdown", + "id": "653acab7", + "metadata": {}, + "source": [ + "f ratio (36.87) > score from f table(3.885)\n", + "\n", + "\n", + "==> Reject H0. Changing the power of the plasma beam DO have significant change on etching rate by the machine'." + ] }, { "cell_type": "markdown", @@ -69,18 +149,462 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "id": "f182b9b4", "metadata": {}, "outputs": [], - "source": [] + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "import warnings\n", + "warnings.filterwarnings('ignore')" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "d8b7fe9e", + "metadata": {}, + "outputs": [], + "source": [ + "data = pd.read_excel('/Users/yuriawano/lab-inferential-statistics-anova/files_for_lab/anova_lab_data.xlsx')" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "3615a978", + "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", + "
PowerEtching Rate
0160 W5.43
1180 W6.24
2200 W8.79
3160 W5.71
4180 W6.71
5200 W9.20
6160 W6.22
7180 W5.98
8200 W7.90
9160 W6.01
10180 W5.66
11200 W8.15
12160 W5.59
13180 W6.60
14200 W7.55
\n", + "
" + ], + "text/plain": [ + " Power Etching Rate\n", + "0 160 W 5.43\n", + "1 180 W 6.24\n", + "2 200 W 8.79\n", + "3 160 W 5.71\n", + "4 180 W 6.71\n", + "5 200 W 9.20\n", + "6 160 W 6.22\n", + "7 180 W 5.98\n", + "8 200 W 7.90\n", + "9 160 W 6.01\n", + "10 180 W 5.66\n", + "11 200 W 8.15\n", + "12 160 W 5.59\n", + "13 180 W 6.60\n", + "14 200 W 7.55" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "e357d741", + "metadata": {}, + "outputs": [], + "source": [ + "data.columns = [columns.lower().replace(' ', '_') for columns in data.columns]" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "a3915641", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Index(['power_', 'etching_rate'], dtype='object')" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.columns" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "c14dde53", + "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", + "
etching_rate
count15.000000
mean6.782667
std1.228643
min5.430000
25%5.845000
50%6.240000
75%7.725000
max9.200000
\n", + "
" + ], + "text/plain": [ + " etching_rate\n", + "count 15.000000\n", + "mean 6.782667\n", + "std 1.228643\n", + "min 5.430000\n", + "25% 5.845000\n", + "50% 6.240000\n", + "75% 7.725000\n", + "max 9.200000" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "67b4fe44", + "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", + "
etching_rate
power_
160 W5.792
180 W6.238
200 W8.318
\n", + "
" + ], + "text/plain": [ + " etching_rate\n", + "power_ \n", + "160 W 5.792\n", + "180 W 6.238\n", + "200 W 8.318" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.groupby('power_').agg(np.mean)" + ] + }, + { + "cell_type": "markdown", + "id": "5e02e2a6", + "metadata": {}, + "source": [ + "Here we find that the by increading the power the etching rate increases.\n", + "Now conduct anova and see if that is true." + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "49daa024", + "metadata": {}, + "outputs": [], + "source": [ + "import statsmodels.api as sm\n", + "from statsmodels.formula.api import ols\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "0092a1c1", + "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", + "
dfsum_sqmean_sqFPR(>F)
C(power_)2.018.1766539.08832736.8789550.000008
Residual12.02.9572400.246437NaNNaN
\n", + "
" + ], + "text/plain": [ + " df sum_sq mean_sq F PR(>F)\n", + "C(power_) 2.0 18.176653 9.088327 36.878955 0.000008\n", + "Residual 12.0 2.957240 0.246437 NaN NaN" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "model = ols('etching_rate ~ C(power_)',data=data).fit()\n", + "sm.stats.anova_lm(model)" + ] + }, + { + "cell_type": "markdown", + "id": "d813462d", + "metadata": {}, + "source": [ + "### Results\n", + "f ratio (36.87) > score from f table(3.885)\n", + "\n", + "==> Reject H0. Changing the power of the plasma beam DO have significant change on etching rate by the machine'." + ] } ], "metadata": { "kernelspec": { - "display_name": "ironhack", + "display_name": "Python 3", "language": "python", - "name": "ironhack" + "name": "python3" }, "language_info": { "codemirror_mode": { @@ -92,7 +616,20 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.8.5" + "version": "3.8.8" + }, + "toc": { + "base_numbering": 1, + "nav_menu": {}, + "number_sections": true, + "sideBar": true, + "skip_h1_title": false, + "title_cell": "Table of Contents", + "title_sidebar": "Contents", + "toc_cell": false, + "toc_position": {}, + "toc_section_display": true, + "toc_window_display": true } }, "nbformat": 4, diff --git a/Untitled.ipynb b/Untitled.ipynb index 7b5f0b3..a14e344 100644 --- a/Untitled.ipynb +++ b/Untitled.ipynb @@ -41,20 +41,100 @@ ] }, { - "cell_type": "code", - "execution_count": null, - "id": "f56d81a7", + "cell_type": "markdown", + "id": "8711159a", "metadata": {}, - "outputs": [], - "source": [] + "source": [ + "### Steps to follow\n", + "\n", + "1. Define the null hypothesis: \n", + "'The means are similar. Changing the power of the plasma beam does NOT have significant change on etching rate by the machine'\n", + "\n", + "2. Define the alternative hypothesis: \n", + "'The means are different. Changing the power of the plasma beam DO have significant change on etching rate by the machine'\n", + "\n", + "3. Level of significent:\n", + "0.05 ( 95% )\n", + "\n", + "4. Degrees of freedom of model, error terms, and total DoF\n", + "4.1 Degrees of freedom (rows - 1) * (columns - 1) --> (15 - 1) * (2 - 1) = 14\n", + "\n", + "4.2 Error terms\n", + "\n", + "4.3 Total DoF\n", + "\n", + "\n", + "\n" + ] }, { - "cell_type": "code", - "execution_count": null, - "id": "a891a030", + "cell_type": "markdown", + "id": "f4ee91dd", "metadata": {}, - "outputs": [], - "source": [] + "source": [ + "### Calculation of F ratio (F statistics)\n", + "\n", + "\n", + "\n", + "#### Groups\t\t\t\n", + "- 160w:\t5\t\t\n", + "- 180w:\t5\t\t\n", + "- 200w:\t5\t\t\n", + "\t\t\t\n", + "#### How to calculate f ratio\n", + "\n", + "1) Cx:\tTotal of etching rate *2 / data points\t--> 690.0685067\n", + "\n", + "2) SSt: Total of square - Cx\t-->\t21.13389333\n", + "\n", + "3) Ssa: SUM(Total score of square in each group / group number (K)) - Cx\t\t\n", + "\t160w\t167.73632\t\n", + "\t180w\t194.56322\t\n", + "\t200w\t345.94562\t\n", + "\tSUM\t708.24516\t\n", + " \n", + "4) SSa= (SUM - Cx) = 18.17665333\n", + "\n", + "5) SSw:\tSSt - Ssa\t=\t2.95724\n", + "\n", + "6) MSSa:\tSSa/(k-1)\t=\t9.088326667\n", + "\n", + "7) MSSw:\tSSw/(n-k)\t=\t0.246436667\n", + "\n", + "8) f ratio:\tMSSa/MSSw\t=\t36.8789547" + ] + }, + { + "cell_type": "markdown", + "id": "9b68ddbe", + "metadata": {}, + "source": [ + "### Check the f table\n", + "- DoF1 = K - 1 = 3 - 1 = 2\n", + "- DoF2 = n - K = 15 - 3 = 12\n", + "\n", + "\n", + "F score = 3.885" + ] + }, + { + "cell_type": "markdown", + "id": "30bea853", + "metadata": {}, + "source": [ + "### Results" + ] + }, + { + "cell_type": "markdown", + "id": "653acab7", + "metadata": {}, + "source": [ + "f ratio (36.87) > score from f table(3.885)\n", + "\n", + "\n", + "==> Reject H0. Changing the power of the plasma beam DO have significant change on etching rate by the machine'." + ] }, { "cell_type": "markdown", @@ -69,18 +149,462 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "id": "f182b9b4", "metadata": {}, "outputs": [], - "source": [] + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "import warnings\n", + "warnings.filterwarnings('ignore')" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "d8b7fe9e", + "metadata": {}, + "outputs": [], + "source": [ + "data = pd.read_excel('/Users/yuriawano/lab-inferential-statistics-anova/files_for_lab/anova_lab_data.xlsx')" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "3615a978", + "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", + "
PowerEtching Rate
0160 W5.43
1180 W6.24
2200 W8.79
3160 W5.71
4180 W6.71
5200 W9.20
6160 W6.22
7180 W5.98
8200 W7.90
9160 W6.01
10180 W5.66
11200 W8.15
12160 W5.59
13180 W6.60
14200 W7.55
\n", + "
" + ], + "text/plain": [ + " Power Etching Rate\n", + "0 160 W 5.43\n", + "1 180 W 6.24\n", + "2 200 W 8.79\n", + "3 160 W 5.71\n", + "4 180 W 6.71\n", + "5 200 W 9.20\n", + "6 160 W 6.22\n", + "7 180 W 5.98\n", + "8 200 W 7.90\n", + "9 160 W 6.01\n", + "10 180 W 5.66\n", + "11 200 W 8.15\n", + "12 160 W 5.59\n", + "13 180 W 6.60\n", + "14 200 W 7.55" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "e357d741", + "metadata": {}, + "outputs": [], + "source": [ + "data.columns = [columns.lower().replace(' ', '_') for columns in data.columns]" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "a3915641", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Index(['power_', 'etching_rate'], dtype='object')" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.columns" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "c14dde53", + "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", + "
etching_rate
count15.000000
mean6.782667
std1.228643
min5.430000
25%5.845000
50%6.240000
75%7.725000
max9.200000
\n", + "
" + ], + "text/plain": [ + " etching_rate\n", + "count 15.000000\n", + "mean 6.782667\n", + "std 1.228643\n", + "min 5.430000\n", + "25% 5.845000\n", + "50% 6.240000\n", + "75% 7.725000\n", + "max 9.200000" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "67b4fe44", + "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", + "
etching_rate
power_
160 W5.792
180 W6.238
200 W8.318
\n", + "
" + ], + "text/plain": [ + " etching_rate\n", + "power_ \n", + "160 W 5.792\n", + "180 W 6.238\n", + "200 W 8.318" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.groupby('power_').agg(np.mean)" + ] + }, + { + "cell_type": "markdown", + "id": "5e02e2a6", + "metadata": {}, + "source": [ + "Here we find that the by increading the power the etching rate increases.\n", + "Now conduct anova and see if that is true." + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "49daa024", + "metadata": {}, + "outputs": [], + "source": [ + "import statsmodels.api as sm\n", + "from statsmodels.formula.api import ols\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "0092a1c1", + "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", + "
dfsum_sqmean_sqFPR(>F)
C(power_)2.018.1766539.08832736.8789550.000008
Residual12.02.9572400.246437NaNNaN
\n", + "
" + ], + "text/plain": [ + " df sum_sq mean_sq F PR(>F)\n", + "C(power_) 2.0 18.176653 9.088327 36.878955 0.000008\n", + "Residual 12.0 2.957240 0.246437 NaN NaN" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "model = ols('etching_rate ~ C(power_)',data=data).fit()\n", + "sm.stats.anova_lm(model)" + ] + }, + { + "cell_type": "markdown", + "id": "d813462d", + "metadata": {}, + "source": [ + "### Results\n", + "f ratio (36.87) > score from f table(3.885)\n", + "\n", + "==> Reject H0. Changing the power of the plasma beam DO have significant change on etching rate by the machine'." + ] } ], "metadata": { "kernelspec": { - "display_name": "ironhack", + "display_name": "Python 3", "language": "python", - "name": "ironhack" + "name": "python3" }, "language_info": { "codemirror_mode": { @@ -92,7 +616,20 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.8.5" + "version": "3.8.8" + }, + "toc": { + "base_numbering": 1, + "nav_menu": {}, + "number_sections": true, + "sideBar": true, + "skip_h1_title": false, + "title_cell": "Table of Contents", + "title_sidebar": "Contents", + "toc_cell": false, + "toc_position": {}, + "toc_section_display": true, + "toc_window_display": true } }, "nbformat": 4, diff --git a/files_for_lab/anova_lab_data.xlsx b/files_for_lab/anova_lab_data.xlsx index 4be5583..e97d9b8 100644 Binary files a/files_for_lab/anova_lab_data.xlsx and b/files_for_lab/anova_lab_data.xlsx differ diff --git a/files_for_lab/anova_lab_data_editedddd.xlsx b/files_for_lab/anova_lab_data_editedddd.xlsx new file mode 100644 index 0000000..d1d75fc Binary files /dev/null and b/files_for_lab/anova_lab_data_editedddd.xlsx differ