diff --git a/notebooks/Solutions/seaborn_TP_solutions.ipynb b/notebooks/Solutions/seaborn_TP_solutions.ipynb
index 5ebf0fa0c645800b6604ebd3ecceb4f1bd7764a9..d96cdf7286b6acb1f0bd577db8472e48b27bc839 100644
--- a/notebooks/Solutions/seaborn_TP_solutions.ipynb
+++ b/notebooks/Solutions/seaborn_TP_solutions.ipynb
@@ -10,11 +10,11 @@
"<div style=\"text-align:center\">\n",
" <img src=\"../images/seaborn.png\" width=\"600px\">\n",
" <div>\n",
- " Bertrand Néron, François Laurent, Etienne Kornobis\n",
+ " Bertrand Néron, François Laurent, Etienne Kornobis, Vincent Guillemot\n",
" <br />\n",
" <a src=\" https://research.pasteur.fr/en/team/bioinformatics-and-biostatistics-hub/\">Bioinformatics and Biostatistiqucs HUB</a>\n",
" <br />\n",
- " © Institut Pasteur, 2021\n",
+ " © Institut Pasteur, 2024\n",
" </div> \n",
"</div>"
]
@@ -24,12 +24,22 @@
"id": "compliant-basis",
"metadata": {},
"source": [
- "Practice your graphing skills using data from milieu intérieur in `data/mi.csv`:"
+ "Practice your graphing skills through the data of [happiness 2016](https://www.kaggle.com/datasets/unsdsn/world-happiness?select=2016.csv)\n",
+ "\n",
+ "(The data are already in data directory as `happiness_2016.csv`)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "3778963b-3bae-486d-8db7-30f23eb239ac",
+ "metadata": {},
+ "source": [
+ "## Import the data and have a look on them"
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 2,
"id": "minor-doctrine",
"metadata": {},
"outputs": [],
@@ -40,34 +50,199 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "id": "d4500895-2a2c-4ebb-a1fc-153e97769b9d",
+ "execution_count": 3,
+ "id": "skilled-daniel",
"metadata": {},
"outputs": [],
"source": [
- "import warnings\n",
- "warnings.simplefilter(action='ignore', category=FutureWarning, lineno=1498)\n",
- "warnings.simplefilter(action='ignore', category=UserWarning, lineno=118)"
+ "ha_df = pd.read_csv(\"../data/happiness_2016.csv\")"
]
},
{
"cell_type": "code",
- "execution_count": null,
- "id": "skilled-daniel",
+ "execution_count": 4,
+ "id": "f8729a5b-314d-42fc-b130-783ca5e2076a",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(157, 13)"
+ ]
+ },
+ "execution_count": 4,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "mi_df = pd.read_csv(\"../data/mi.csv\")"
+ "ha_df.shape"
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 5,
"id": "brutal-manufacturer",
"metadata": {},
- "outputs": [],
- "source": [
- "mi_df.head()"
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Country</th>\n",
+ " <th>Region</th>\n",
+ " <th>Happiness Rank</th>\n",
+ " <th>Happiness Score</th>\n",
+ " <th>Lower Confidence Interval</th>\n",
+ " <th>Upper Confidence Interval</th>\n",
+ " <th>Economy (GDP per Capita)</th>\n",
+ " <th>Family</th>\n",
+ " <th>Health (Life Expectancy)</th>\n",
+ " <th>Freedom</th>\n",
+ " <th>Trust (Government Corruption)</th>\n",
+ " <th>Generosity</th>\n",
+ " <th>Dystopia Residual</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Denmark</td>\n",
+ " <td>Western Europe</td>\n",
+ " <td>1</td>\n",
+ " <td>7.526</td>\n",
+ " <td>7.460</td>\n",
+ " <td>7.592</td>\n",
+ " <td>1.44178</td>\n",
+ " <td>1.16374</td>\n",
+ " <td>0.79504</td>\n",
+ " <td>0.57941</td>\n",
+ " <td>0.44453</td>\n",
+ " <td>0.36171</td>\n",
+ " <td>2.73939</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Switzerland</td>\n",
+ " <td>Western Europe</td>\n",
+ " <td>2</td>\n",
+ " <td>7.509</td>\n",
+ " <td>7.428</td>\n",
+ " <td>7.590</td>\n",
+ " <td>1.52733</td>\n",
+ " <td>1.14524</td>\n",
+ " <td>0.86303</td>\n",
+ " <td>0.58557</td>\n",
+ " <td>0.41203</td>\n",
+ " <td>0.28083</td>\n",
+ " <td>2.69463</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Iceland</td>\n",
+ " <td>Western Europe</td>\n",
+ " <td>3</td>\n",
+ " <td>7.501</td>\n",
+ " <td>7.333</td>\n",
+ " <td>7.669</td>\n",
+ " <td>1.42666</td>\n",
+ " <td>1.18326</td>\n",
+ " <td>0.86733</td>\n",
+ " <td>0.56624</td>\n",
+ " <td>0.14975</td>\n",
+ " <td>0.47678</td>\n",
+ " <td>2.83137</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Norway</td>\n",
+ " <td>Western Europe</td>\n",
+ " <td>4</td>\n",
+ " <td>7.498</td>\n",
+ " <td>7.421</td>\n",
+ " <td>7.575</td>\n",
+ " <td>1.57744</td>\n",
+ " <td>1.12690</td>\n",
+ " <td>0.79579</td>\n",
+ " <td>0.59609</td>\n",
+ " <td>0.35776</td>\n",
+ " <td>0.37895</td>\n",
+ " <td>2.66465</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>Finland</td>\n",
+ " <td>Western Europe</td>\n",
+ " <td>5</td>\n",
+ " <td>7.413</td>\n",
+ " <td>7.351</td>\n",
+ " <td>7.475</td>\n",
+ " <td>1.40598</td>\n",
+ " <td>1.13464</td>\n",
+ " <td>0.81091</td>\n",
+ " <td>0.57104</td>\n",
+ " <td>0.41004</td>\n",
+ " <td>0.25492</td>\n",
+ " <td>2.82596</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Country Region Happiness Rank Happiness Score \\\n",
+ "0 Denmark Western Europe 1 7.526 \n",
+ "1 Switzerland Western Europe 2 7.509 \n",
+ "2 Iceland Western Europe 3 7.501 \n",
+ "3 Norway Western Europe 4 7.498 \n",
+ "4 Finland Western Europe 5 7.413 \n",
+ "\n",
+ " Lower Confidence Interval Upper Confidence Interval \\\n",
+ "0 7.460 7.592 \n",
+ "1 7.428 7.590 \n",
+ "2 7.333 7.669 \n",
+ "3 7.421 7.575 \n",
+ "4 7.351 7.475 \n",
+ "\n",
+ " Economy (GDP per Capita) Family Health (Life Expectancy) Freedom \\\n",
+ "0 1.44178 1.16374 0.79504 0.57941 \n",
+ "1 1.52733 1.14524 0.86303 0.58557 \n",
+ "2 1.42666 1.18326 0.86733 0.56624 \n",
+ "3 1.57744 1.12690 0.79579 0.59609 \n",
+ "4 1.40598 1.13464 0.81091 0.57104 \n",
+ "\n",
+ " Trust (Government Corruption) Generosity Dystopia Residual \n",
+ "0 0.44453 0.36171 2.73939 \n",
+ "1 0.41203 0.28083 2.69463 \n",
+ "2 0.14975 0.47678 2.83137 \n",
+ "3 0.35776 0.37895 2.66465 \n",
+ "4 0.41004 0.25492 2.82596 "
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "ha_df.head()"
]
},
{
@@ -75,7 +250,7 @@
"id": "departmental-exhibition",
"metadata": {},
"source": [
- "- Do a boxplot showing the differences in temperature between females and males:"
+ "## Do a boxplot showing the differences in `happiness` between `Region`:"
]
},
{
@@ -85,7 +260,7 @@
"metadata": {},
"outputs": [],
"source": [
- "sns.boxplot(data=mi_df, x=\"Sex\", y=\"Temperature\")"
+ "sns.boxplot(data=ha_df, x=\"Happiness Score\", y=\"Region\")"
]
},
{
@@ -93,7 +268,7 @@
"id": "portuguese-worse",
"metadata": {},
"source": [
- "- Using a histogram and continuous probability density curve, display the distribution of age in the dataset"
+ "## Using a histogram and continuous probability density curve, display the distribution of `Freedom` in the dataset"
]
},
{
@@ -103,7 +278,7 @@
"metadata": {},
"outputs": [],
"source": [
- "sns.histplot(data=mi_df, x=\"Age\")"
+ "sns.histplot(data=ha_df, x=\"Freedom\")"
]
},
{
@@ -113,7 +288,7 @@
"metadata": {},
"outputs": [],
"source": [
- "sns.histplot(data=mi_df, x=\"Age\", kde=True)"
+ "sns.histplot(data=ha_df, x=\"Freedom\", kde=True)"
]
},
{
@@ -121,7 +296,7 @@
"id": "prepared-stephen",
"metadata": {},
"source": [
- "- Use a barplot to show the count of vaccinated for yellow fever (see the documentation for a countplot)"
+ "- Use a barplot to show the count of country per Region (see the documentation for a countplot)"
]
},
{
@@ -131,527 +306,501 @@
"metadata": {},
"outputs": [],
"source": [
- "sns.countplot(data=mi_df, x=\"VaccineYellowFever\")"
+ "sns.countplot(data=ha_df, x=\"Region\")"
]
},
{
"cell_type": "markdown",
- "id": "immediate-method",
+ "id": "4e1d16f2-57d8-4f0e-9a69-e9ab193a3ebc",
"metadata": {},
"source": [
- "- Plot the distribution of age for the people vaccinated for the flu"
+ "As you can see the labels overlaps each ohers and are not readable\n",
+ "\n",
+ "One possibility is to rotate the X-labels. In this case is better to provide the labels."
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "academic-measure",
+ "id": "64ee74bb-5f37-485f-8c03-d06ac14d3010",
"metadata": {},
"outputs": [],
"source": [
- "sns.histplot(data=mi_df.query(\"VaccineFlu == 'Yes'\"), x=\"Age\", kde=True)"
+ "# extract the Region from the data, I will use them as labels for figures below\n",
+ "regions = ha_df.loc[:, 'Region'].drop_duplicates()"
]
},
{
- "cell_type": "markdown",
- "id": "temporal-synthesis",
- "metadata": {},
- "source": [
- "- Feel free to explore more of [seaborn](https://seaborn.pydata.org/examples/index.html) !"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "db56d49a-4770-4f9e-af6b-78960574d338",
- "metadata": {},
- "source": [
- "# Exploring count matrices from RNA-seq data"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "5377668b-dea5-4c20-8249-5266f98774eb",
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "eb7c96ac-585a-4787-a2ee-dec3d04790ca",
"metadata": {},
+ "outputs": [],
"source": [
- "<img src=\"../images/rnaseq.png\" style=\"margin:0 auto;width:800px\">"
+ "ax = sns.countplot(data=ha_df, x=\"Region\")\n",
+ "ax.set_xticks(regions)\n",
+ "ax.set_xticklabels(regions, rotation=45, ha='right', rotation_mode='anchor')"
]
},
{
"cell_type": "markdown",
- "id": "ebf1606b-0b21-4821-a899-551ec33c977e",
+ "id": "e2eac27c-2de9-4942-82b9-294318ec5fd4",
"metadata": {},
"source": [
- "- Import the count_matrix tsv file from the data folder"
+ "## On the same data `Happiness` and `Region` do a boxplot and a swarmplot to display the structure of the data"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "3e0fe80a-175f-4cec-96f9-28bd7005097d",
+ "id": "b0fd6058-65b0-4f9b-bc59-dce0193f1580",
"metadata": {},
"outputs": [],
"source": [
- "counts_df = pd.read_csv(\"../data/count_matrix.tsv\", sep=\"\\t\")"
+ "ax = sns.swarmplot(data=ha_df, x=\"Region\", y=\"Happiness Score\")\n",
+ "ax.set_xticks(regions)\n",
+ "ax.set_xticklabels(regions,rotation=45, ha='right', rotation_mode='anchor')"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "671736af-d00e-475a-9670-86374402a741",
+ "id": "1fe079b4-013a-4d48-ac31-9daad4b4673e",
"metadata": {},
"outputs": [],
"source": [
- "counts_df"
+ "ax = sns.boxplot(data=ha_df, x=\"Region\", y=\"Happiness Score\", hue='Region') # see the result of the option hue\n",
+ "ax.set_xticks(regions)\n",
+ "ax.set_xticklabels(regions,rotation=45, ha='right', rotation_mode='anchor')"
]
},
{
"cell_type": "markdown",
- "id": "c80d9947-9ccf-4499-a1c2-9194377cd054",
- "metadata": {},
- "source": [
- "- Simplify the dataframe to only have the \"Geneid\", \"WTx\" and \"Cx\" columns"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "01a3b73d-46cb-48e7-8f18-2c8a6a612724",
+ "id": "immediate-method",
"metadata": {},
- "outputs": [],
"source": [
- "counts_df.drop([\"Chr\", \"Start\", \"End\", \"Strand\", \"Length\"], axis=1, inplace=True)"
+ "## Plot the distribution of `happiness` for the people leaving `Western Europe`"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "997274c0-63ed-492f-94ea-f6bdd8552455",
+ "id": "academic-measure",
"metadata": {},
"outputs": [],
"source": [
- "counts_df"
+ "sns.histplot(data=ha_df.query(\"Region == 'Western Europe'\"), x=\"Happiness Score\", kde=True)"
]
},
{
"cell_type": "markdown",
- "id": "eb65b51f-f689-4a66-b47c-e79f0e9eba52",
+ "id": "fd9789db-9bab-478a-bcec-1c8b6775cf20",
"metadata": {},
"source": [
- "- Format properly your DataFrame to be able to use https://seaborn.pydata.org/generated/seaborn.clustermap.html to realize a heatmap."
+ "## Plot the `Health (Life Expectancy)` vs `Happiness Score` and color the dots according to the region "
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "49f81fab-0e9e-4add-a0b6-249b735c7ab8",
+ "id": "d42f72f1-1d01-496e-89a1-68391ffa4281",
"metadata": {},
"outputs": [],
"source": [
- "counts_df.set_index(\"Geneid\", inplace=True)"
+ "import matplotlib.pyplot as plt"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "467a2115-6735-4a7f-aaf6-bbc1029a57a2",
+ "id": "52ae8376-3c66-4ca6-86a9-f9ae9f56076f",
"metadata": {},
"outputs": [],
"source": [
- "counts_df"
+ "fig, ax = plt.subplots(figsize=(9, 7))\n",
+ "sns.scatterplot(data=ha_df, x=\"Health (Life Expectancy)\", y=\"Happiness Score\", hue=\"Region\", ax=ax)"
]
},
{
- "cell_type": "code",
- "execution_count": null,
- "id": "79ae3c32-ce30-49d0-882b-e5681a50fef8",
+ "cell_type": "markdown",
+ "id": "temporal-synthesis",
"metadata": {},
- "outputs": [],
"source": [
- "sns.clustermap(data=counts_df)"
+ "- Feel free to explore more of [seaborn](https://seaborn.pydata.org/examples/index.html) !"
]
},
{
"cell_type": "markdown",
- "id": "f8d6188e-3a37-4ba5-b377-a11696054e9c",
+ "id": "3063abf7-2251-48eb-b371-6c5b70b45fe7",
"metadata": {},
"source": [
- "- Explore the clustermap documentation to have a more visual heatmap by standardizing the data within genes."
+ "## Do a barplot of the Happiness Score for each Region"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "d1c055d5-0608-4bc3-ac33-738848946639",
+ "id": "85dd0df6-74e7-43be-9a7c-eb922a06601b",
"metadata": {},
"outputs": [],
"source": [
- "sns.clustermap(data=counts_df, z_score=0)"
+ "sns.barplot(data=ha_df, y=\"Region\", x=\"Happiness Score\", hue='Region', orient='h')"
]
},
{
"cell_type": "markdown",
- "id": "2e61a207-223a-4c01-88ea-76b1b8c3a0b9",
- "metadata": {},
- "source": [
- "- Reformat the counts_df dataframe to have genes in columns and samples in rows.\n",
- "- Add a \"group\" column defining the grouping of the samples:\n",
- " - \"WTx\" samples will be from the \"WT\" group.\n",
- " - \"Cx\" samples will be from the \"C\" group."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "59d107fa-7246-4c58-98d2-573313499034",
+ "id": "3ee5741a-64f4-4690-963b-1f7e729398bf",
"metadata": {},
- "outputs": [],
"source": [
- "counts_df = counts_df.T"
+ "## from this point we will focus on the Regions\n",
+ "\n",
+ "### clean our dataset. Remove not relevant columns"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "6744918a-098d-40b0-a6a6-0774c6c3df16",
+ "id": "0344b730-1535-47fb-82f5-07003fd223f9",
"metadata": {},
"outputs": [],
"source": [
- "counts_df.sort_index(inplace=True)"
+ "ha_df.columns"
]
},
{
- "cell_type": "code",
- "execution_count": null,
- "id": "7100ab14-e759-4b12-9e39-f4e422fdb070",
+ "cell_type": "markdown",
+ "id": "36e449d1-0add-4ebc-8903-d535219ce423",
"metadata": {},
- "outputs": [],
"source": [
- "counts_df.loc[:,\"groups\"] = [\"C\", \"C\", \"C\", \"WT\", \"WT\", \"WT\"]"
+ "1. keep only columns 'Region', 'Happiness Score', 'Economy (GDP per Capita)', 'Family', 'Freedom','Trust (Government Corruption)', 'Generosity'\n",
+ "2. set the index to the Region\n",
+ "3. have a look on your new data"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "4a42b339-3ed8-4b7f-b5f9-f8a4eed8dd6c",
+ "id": "bdf897c4-b8f3-4dff-b9c0-0ad47b25ecc0",
"metadata": {},
"outputs": [],
"source": [
- "counts_df"
+ "region_df = ha_df.loc[:, ['Region', 'Happiness Score', 'Economy (GDP per Capita)', 'Family', 'Freedom','Trust (Government Corruption)', 'Generosity']]\n",
+ "region_df.set_index('Region', inplace=True)\n",
+ "region_df.head()"
]
},
{
"cell_type": "markdown",
- "id": "9a88ecb1-9ed3-4160-91ee-24a30e994b71",
+ "id": "e1ae03ac-ac7c-436d-987d-113e9cca3eec",
"metadata": {},
"source": [
- "- Display a barplot showing the mean expression for each group for a particular gene (for example \"gene-LEPBI_RS00065\")."
+ "## Aggregate the new data region by region. Compute the mean of each country as value for the corresponding Region"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "924a1a92-5cba-4796-b6c0-bbf849112434",
+ "id": "3fc3ea89-a448-4e7b-abfb-3fa92cffc5f7",
"metadata": {},
"outputs": [],
"source": [
- "sns.barplot(data=counts_df, x=\"groups\", y=\"gene-LEPBI_RS00065\")"
+ "reg_agg = region_df.groupby('Region').agg('mean')\n",
+ "reg_agg"
]
},
{
"cell_type": "markdown",
- "id": "99e2455a-cb7d-44d5-a4a0-2cf272c814ab",
+ "id": "97cb188c-3e50-4492-961f-cadea3611aaa",
"metadata": {},
"source": [
- "- Try plotting a swarmplot on top of the previous barplot:"
+ "## Do a hierarchically-clustered heatmap "
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "7102bd62-f2d1-4573-a741-45903b9dee1d",
+ "id": "9aa21ed4-e9b2-4eb3-a693-c59ceb513552",
"metadata": {},
"outputs": [],
"source": [
- "sns.barplot(data=counts_df, x=\"groups\", y=\"gene-LEPBI_RS00065\")\n",
- "sns.swarmplot(data=counts_df, x=\"groups\", y=\"gene-LEPBI_RS00065\")"
+ "sns.clustermap(data=reg_agg)"
]
},
{
"cell_type": "markdown",
- "id": "d200d375-362e-4c1d-a88e-130b094e6feb",
+ "id": "88d27d29-e3b8-43d7-8324-25e50c247872",
"metadata": {},
"source": [
- "- Now plot the same data using a boxplot. Can you see the problem of displaying boxplots for this kind of data ?"
+ "Check the data."
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "6cb35e0f-eb0f-4d66-8808-996b1c89c894",
+ "id": "0128f575-0b2a-4cbc-8f6e-8b7e22d81254",
"metadata": {},
"outputs": [],
"source": [
- "sns.boxplot(data=counts_df, x=\"groups\", y=\"gene-LEPBI_RS00065\")"
+ "reg_agg.describe()"
]
},
{
"cell_type": "markdown",
- "id": "2e1cabe0-aab7-4f0e-888e-81aae7d5df8d",
+ "id": "f9b39ab8-0051-4840-9e87-fe2bcb8ca07a",
"metadata": {},
"source": [
- "- Compute the median of each genes by groups:"
+ "The data are not in the same range, so it could be better to standardize the data before to do the clustering"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "a5a896e2-2133-4365-bc78-43bee7f253a7",
+ "id": "ff4beb57-b357-47a3-b7bd-877e05229b6b",
"metadata": {},
"outputs": [],
"source": [
- "med_counts_df = counts_df.groupby(\"groups\").median().T"
+ "normalized_reg=(reg_agg - reg_agg.mean()) / reg_agg.std()\n",
+ "normalized_reg"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "572d74c5-f612-4494-9ece-b6f80fd1cd6d",
+ "id": "e19f9472-cb9b-434b-8689-2bf09d49b902",
"metadata": {},
"outputs": [],
"source": [
- "med_counts_df"
+ "sns.clustermap(data=normalized_reg, annot=True) # see the results of the annot option "
]
},
{
"cell_type": "markdown",
- "id": "308cc10b-6727-4bc5-b05d-4777037e252e",
+ "id": "d64a0377-339b-4fe7-beb4-a32e4a4e0113",
"metadata": {},
"source": [
- "We are going now to add extra annotations to this median table in order to identify genes of interest.\n",
- "- Import the annotation.csv table from the data folder: "
+ "It's possible to do that directly in seaborn. with the option z_score (https://seaborn.pydata.org/generated/seaborn.clustermap.html)"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "a52c17a1-59bd-4fd7-9b7b-1ba98b194399",
+ "id": "3b439517-5007-4fbb-828d-265f9835594f",
"metadata": {},
"outputs": [],
"source": [
- "annot_df = pd.read_csv(\"../data/annotations.csv\", index_col=0)"
+ "sns.clustermap(data=reg_agg, z_score=1, annot=True)"
]
},
{
"cell_type": "markdown",
- "id": "50fa81a7-3f34-4160-ad2d-f77d21be9ac0",
+ "id": "f8d6188e-3a37-4ba5-b377-a11696054e9c",
"metadata": {},
"source": [
- "Annotations in this table are available for many types of loci (the \"genetic_type\" column), but here we will focus on the \"gene\" genetic_type. \n",
- "- Filter the annotation dataframe to have only \"gene\" as \"genetic_type\"."
+ "- Explore the clustermap documentation to have a more visual heatmap by standardizing the data within genes."
]
},
{
- "cell_type": "code",
- "execution_count": null,
- "id": "2606146d-daf9-4e99-a4f3-722b16d6ecba",
+ "cell_type": "markdown",
+ "id": "a2627322-e6a5-422f-8a69-b89dbd4b777e",
"metadata": {},
- "outputs": [],
"source": [
- "annot_df = annot_df.query(\"genetic_type == 'gene'\")"
+ "## Create a function which produce a single image with four different plots of your choice and save it to pdf file.\n",
+ "\n",
+ "like the image below."
]
},
{
- "cell_type": "code",
- "execution_count": null,
- "id": "74581155-e29d-48d1-8548-dc8186db35e2",
+ "cell_type": "markdown",
+ "id": "4121ff3d-6814-493e-a505-357ad81b0d28",
"metadata": {},
- "outputs": [],
"source": [
- "annot_df"
+ "<img src=\"../images/multiple_figure.png\" width=\"50%\" />"
]
},
{
- "cell_type": "markdown",
- "id": "f8a4e744-e7e2-43b6-b3d4-e59feb40d3ff",
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "a322c866-9232-4fae-bcee-9a635e3fd70b",
"metadata": {},
+ "outputs": [],
"source": [
- "- Concatenate the dataframe with median by group and the annotation dataframe together:"
+ "import matplotlib.pyplot as plt"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "cfd41f82-0e31-41f9-8e1c-75cc934e89d2",
+ "id": "044022d1-741d-4a07-ba7f-c1f863cca138",
"metadata": {},
"outputs": [],
"source": [
- "total_df = pd.concat([med_counts_df, annot_df.set_index(\"ID\")], axis=1, join=\"inner\")"
+ "def expression_graph():\n",
+ " fig, axs = plt.subplots(2,2, figsize=(9,7), constrained_layout=True) # constrained_layout=True avoid overlapping between axis title and X-labels from the above figure\n",
+ " sns.boxplot(data=ha_df, x=\"Happiness Score\", y=\"Region\", hue='Region', ax=axs[0,0])\n",
+ " axs[0,0].set_title(\"happiness data structure\")\n",
+ " \n",
+ " sns.scatterplot(data=ha_df, x=\"Health (Life Expectancy)\", y=\"Happiness Score\", hue=\"Region\", legend=False, ax=axs[0,1])\n",
+ " axs[0,1].set_title(\"Happiness vs Health\")\n",
+ " \n",
+ " sns.barplot(data=ha_df, y=\"Region\", x=\"Happiness Score\", hue='Region', orient='h', ax=axs[1,0])\n",
+ " axs[1,0].set_title(\"happiness through the world\")\n",
+ " \n",
+ " sns.histplot(data=ha_df, x=\"Happiness Score\", kde=True, ax=axs[1,1])\n",
+ " axs[1,1].set_title(\"Happiness data distribution\")\n",
+ " \n",
+ " return fig\n",
+ " "
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "e2d779f7-c127-4f24-8e6c-34190bf8460d",
- "metadata": {
- "tags": []
- },
+ "id": "c33bfc78-7480-4327-93a0-f8aaca0d3614",
+ "metadata": {},
"outputs": [],
"source": [
- "total_df"
+ "my_fig = expression_graph()\n",
+ "my_fig.suptitle(\"Happiness Report\")\n",
+ "my_fig.savefig(\"happiness_visualization.pdf\", bbox_inches = \"tight\") # bbox_inches = \"tight\" avoid to truncate the Y-labels on left on pdf"
]
},
{
"cell_type": "markdown",
- "id": "af9f8e1f-5f8b-4152-b08a-44e957f13cec",
+ "id": "0d05aba4-3c85-4cd9-85f3-5296b19308fb",
"metadata": {},
"source": [
- "- Calculate an estimate of the gene expression fold change for each gene (by dividing the C median expressions by WT median expressions).\n",
- "- Add it as a \"FoldChange\" column to the previous dataframe."
+ "# Extras"
]
},
{
- "cell_type": "code",
- "execution_count": null,
- "id": "03e3e893-ae73-4fea-853c-bcdc6129f71c",
+ "cell_type": "markdown",
+ "id": "66d6668e-683f-462e-a72f-28bdda8736f2",
"metadata": {},
- "outputs": [],
"source": [
- "total_df.loc[:, \"FoldChange\"] = total_df.C / total_df.WT"
+ "- Using ipywidget, make a function to display barplot of `Happiness Score` by country but with region selected by the user (using a Dropdown widget)"
]
},
{
"cell_type": "markdown",
- "id": "d70eb26b-0a26-4bbc-af03-ba8781b09fb5",
+ "id": "042bd87e-d2dc-4544-a771-51d80c565d0f",
"metadata": {},
"source": [
- "- Use a barplot to display fold changes and using the new gene annotation (The \"Name\" column)"
+ "Imports the needed modules \n",
+ "- `widgets` and `interact` from the `ipywidgets` package\n"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "e11d36d2-6a41-463b-92e0-af4cdcec279f",
+ "id": "64ebeca1-1332-4585-9e5c-c1b66f82be71",
"metadata": {},
"outputs": [],
"source": [
- "sns.barplot(data=total_df, x=\"FoldChange\", y=\"Name\")"
+ "from ipywidgets import widgets\n",
+ "from ipywidgets import interact"
]
},
{
"cell_type": "markdown",
- "id": "34a26492-7c6b-4a07-a4de-67ec8f693cdc",
+ "id": "277264e6-a173-40c5-b71e-4cd551a7fa99",
"metadata": {},
"source": [
- "- By calculating the length of each gene and using a visualisation, does gene expression appears correlated with gene length ?"
+ "create a dataframe containing regions (without duplicates values"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "9e16ae65-8cd9-42cd-931c-8dd519715255",
+ "id": "ebf7fde9-b4a1-4e8a-86ab-86ad8b1b533a",
"metadata": {},
"outputs": [],
"source": [
- "total_df.loc[:,\"gene_length\"] = total_df.loc[:,\"stop\"] - total_df.loc[:,\"start\"]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "08854b8a-f35c-4ce5-a509-c94d37ceaa2a",
- "metadata": {},
- "outputs": [],
- "source": [
- "sns.relplot(data=total_df, x=\"C\", y=\"gene_length\")"
+ "regions = ha_df.loc[:, 'Region'].drop_duplicates()"
]
},
{
"cell_type": "markdown",
- "id": "a2627322-e6a5-422f-8a69-b89dbd4b777e",
+ "id": "f34e5053-ccf5-4a67-96db-7457fe16bbd6",
"metadata": {},
"source": [
- "- Create a function which produce a single image with four different plots of your choice and save it to pdf file."
+ "1. Use this DataFarame to populate your dropdown list\n",
+ "2. Use the region selected in dropdown list as parameter of your function\n",
+ "3. select form the whole data frame the data corresponding to this region\n",
+ "4. display the barplot"
]
},
{
- "cell_type": "code",
- "execution_count": null,
- "id": "a322c866-9232-4fae-bcee-9a635e3fd70b",
+ "cell_type": "markdown",
+ "id": "feba608f-2ecb-41ae-b04a-12f075fd644b",
"metadata": {},
- "outputs": [],
"source": [
- "import matplotlib.pyplot as plt"
+ "below the code skeleton of your function\n",
+ "\n",
+ "```python\n",
+ "@interact(region=widgets.Dropdown(options=regions))\n",
+ "def plot_counts(region):\n",
+ " data = ha_df.loc[ha_df['Region'] == region]\n",
+ " ax = sns.barplot(data= ....\n",
+ "```"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "044022d1-741d-4a07-ba7f-c1f863cca138",
+ "id": "fb746fda-36cc-4c35-92d8-257a489fb278",
"metadata": {},
"outputs": [],
"source": [
- "def expression_graph():\n",
"\n",
- " fig, axs = plt.subplots(2,2, figsize=(9,7)) # 2 rows, 2 columns\n",
- " sns.barplot(data=total_df, x=\"FoldChange\", y=\"Name\", ax=axs[0,0])\n",
- " sns.barplot(data=counts_df, x=\"groups\", y=\"gene-LEPBI_RS00065\", ax=axs[0,1])\n",
- " sns.swarmplot(data=counts_df, x=\"groups\", y=\"gene-LEPBI_RS00065\", ax=axs[0,1])\n",
- " sns.scatterplot(data=total_df, x=\"WT\", y=\"gene_length\", ax=axs[1,0])\n",
- " sns.scatterplot(data=total_df, x=\"C\", y=\"gene_length\", ax=axs[1,1], color=\"red\")\n",
- " \n",
+ "@interact(region=widgets.Dropdown(options=regions))\n",
+ "def plot_counts(region):\n",
+ " data = ha_df.loc[ha_df['Region'] == region]\n",
+ " ax = sns.barplot(data=data, y='Happiness Score', x='Country')\n",
+ " ax.set_xticks(data.Country)\n",
+ " ax.set_xticklabels(data.Country, rotation=45, ha='right', rotation_mode='anchor')\n",
" "
]
},
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "c33bfc78-7480-4327-93a0-f8aaca0d3614",
- "metadata": {},
- "outputs": [],
- "source": [
- "expression_graph()\n",
- "plt.savefig(\"expression_visualization.pdf\")"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "0d05aba4-3c85-4cd9-85f3-5296b19308fb",
- "metadata": {},
- "source": [
- "# Extras"
- ]
- },
{
"cell_type": "markdown",
- "id": "66d6668e-683f-462e-a72f-28bdda8736f2",
+ "id": "3f4bd68e-eb26-46f8-a00f-86f9d0570580",
"metadata": {},
"source": [
- "- Using ipywidget, make a function to display barplot of gene expression by groups with the gene being selected by the user (using a Dropdown widget for example)."
+ "You can customize your figure as classical seaborn/matplotib figure\n",
+ "\n",
+ "for instance to display the value above each bar"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "64ebeca1-1332-4585-9e5c-c1b66f82be71",
+ "id": "7bcee7c5-f1c2-4035-9b7c-e68e1d73a932",
"metadata": {},
"outputs": [],
"source": [
- "from ipywidgets import widgets\n",
- "from ipywidgets import interact\n",
- "import matplotlib.pyplot as plt"
+ "\n",
+ "@interact(region=widgets.Dropdown(options=regions))\n",
+ "def plot_counts(region):\n",
+ " data = ha_df.loc[ha_df['Region'] == region]\n",
+ " ax = sns.barplot(data=data, y='Happiness Score', x='Country')\n",
+ " for i in ax.containers:\n",
+ " # add label on each bar https://www.geeksforgeeks.org/how-to-show-values-on-seaborn-barplot/\n",
+ " ax.bar_label(i, fmt=\"{:.2f}\", rotation='vertical', padding=3)\n",
+ " \n",
+ " ax.set_xticks(data.Country)\n",
+ " ax.set_xticklabels(data.Country, rotation=45, ha='right', rotation_mode='anchor')\n",
+ " ax.margins(y=0.1) # add margin to avoid to have label outside the barplotboundaries, here add 10% white space vertically \n",
+ " # https://stackoverflow.com/questions/72662991/how-can-i-prevent-bar-labels-from-going-outside-the-barplot-boundaries-range\n",
+ " "
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "fb746fda-36cc-4c35-92d8-257a489fb278",
+ "id": "d78b7b86-ecaa-4d27-80ca-2d3e46c2aca3",
"metadata": {},
"outputs": [],
- "source": [
- "@interact(genes=widgets.Dropdown(options=counts_df.columns))\n",
- "def plot_counts(genes):\n",
- " return plt.show(sns.barplot(data=counts_df, x=\"groups\", y=genes))"
- ]
+ "source": []
}
],
"metadata": {
diff --git a/notebooks/Solutions/seaborn_TP_solutions_happiness2016.ipynb b/notebooks/Solutions/seaborn_TP_solutions_happiness2016.ipynb
deleted file mode 100644
index d96cdf7286b6acb1f0bd577db8472e48b27bc839..0000000000000000000000000000000000000000
--- a/notebooks/Solutions/seaborn_TP_solutions_happiness2016.ipynb
+++ /dev/null
@@ -1,827 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "markdown",
- "id": "instrumental-personal",
- "metadata": {},
- "source": [
- "# <center><b>Hands-on</b></center>\n",
- "\n",
- "<div style=\"text-align:center\">\n",
- " <img src=\"../images/seaborn.png\" width=\"600px\">\n",
- " <div>\n",
- " Bertrand Néron, François Laurent, Etienne Kornobis, Vincent Guillemot\n",
- " <br />\n",
- " <a src=\" https://research.pasteur.fr/en/team/bioinformatics-and-biostatistics-hub/\">Bioinformatics and Biostatistiqucs HUB</a>\n",
- " <br />\n",
- " © Institut Pasteur, 2024\n",
- " </div> \n",
- "</div>"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "compliant-basis",
- "metadata": {},
- "source": [
- "Practice your graphing skills through the data of [happiness 2016](https://www.kaggle.com/datasets/unsdsn/world-happiness?select=2016.csv)\n",
- "\n",
- "(The data are already in data directory as `happiness_2016.csv`)"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "3778963b-3bae-486d-8db7-30f23eb239ac",
- "metadata": {},
- "source": [
- "## Import the data and have a look on them"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "id": "minor-doctrine",
- "metadata": {},
- "outputs": [],
- "source": [
- "import pandas as pd\n",
- "import seaborn as sns"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 3,
- "id": "skilled-daniel",
- "metadata": {},
- "outputs": [],
- "source": [
- "ha_df = pd.read_csv(\"../data/happiness_2016.csv\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 4,
- "id": "f8729a5b-314d-42fc-b130-783ca5e2076a",
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "(157, 13)"
- ]
- },
- "execution_count": 4,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "ha_df.shape"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "id": "brutal-manufacturer",
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "<div>\n",
- "<style scoped>\n",
- " .dataframe tbody tr th:only-of-type {\n",
- " vertical-align: middle;\n",
- " }\n",
- "\n",
- " .dataframe tbody tr th {\n",
- " vertical-align: top;\n",
- " }\n",
- "\n",
- " .dataframe thead th {\n",
- " text-align: right;\n",
- " }\n",
- "</style>\n",
- "<table border=\"1\" class=\"dataframe\">\n",
- " <thead>\n",
- " <tr style=\"text-align: right;\">\n",
- " <th></th>\n",
- " <th>Country</th>\n",
- " <th>Region</th>\n",
- " <th>Happiness Rank</th>\n",
- " <th>Happiness Score</th>\n",
- " <th>Lower Confidence Interval</th>\n",
- " <th>Upper Confidence Interval</th>\n",
- " <th>Economy (GDP per Capita)</th>\n",
- " <th>Family</th>\n",
- " <th>Health (Life Expectancy)</th>\n",
- " <th>Freedom</th>\n",
- " <th>Trust (Government Corruption)</th>\n",
- " <th>Generosity</th>\n",
- " <th>Dystopia Residual</th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th>0</th>\n",
- " <td>Denmark</td>\n",
- " <td>Western Europe</td>\n",
- " <td>1</td>\n",
- " <td>7.526</td>\n",
- " <td>7.460</td>\n",
- " <td>7.592</td>\n",
- " <td>1.44178</td>\n",
- " <td>1.16374</td>\n",
- " <td>0.79504</td>\n",
- " <td>0.57941</td>\n",
- " <td>0.44453</td>\n",
- " <td>0.36171</td>\n",
- " <td>2.73939</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>1</th>\n",
- " <td>Switzerland</td>\n",
- " <td>Western Europe</td>\n",
- " <td>2</td>\n",
- " <td>7.509</td>\n",
- " <td>7.428</td>\n",
- " <td>7.590</td>\n",
- " <td>1.52733</td>\n",
- " <td>1.14524</td>\n",
- " <td>0.86303</td>\n",
- " <td>0.58557</td>\n",
- " <td>0.41203</td>\n",
- " <td>0.28083</td>\n",
- " <td>2.69463</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>2</th>\n",
- " <td>Iceland</td>\n",
- " <td>Western Europe</td>\n",
- " <td>3</td>\n",
- " <td>7.501</td>\n",
- " <td>7.333</td>\n",
- " <td>7.669</td>\n",
- " <td>1.42666</td>\n",
- " <td>1.18326</td>\n",
- " <td>0.86733</td>\n",
- " <td>0.56624</td>\n",
- " <td>0.14975</td>\n",
- " <td>0.47678</td>\n",
- " <td>2.83137</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>3</th>\n",
- " <td>Norway</td>\n",
- " <td>Western Europe</td>\n",
- " <td>4</td>\n",
- " <td>7.498</td>\n",
- " <td>7.421</td>\n",
- " <td>7.575</td>\n",
- " <td>1.57744</td>\n",
- " <td>1.12690</td>\n",
- " <td>0.79579</td>\n",
- " <td>0.59609</td>\n",
- " <td>0.35776</td>\n",
- " <td>0.37895</td>\n",
- " <td>2.66465</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>4</th>\n",
- " <td>Finland</td>\n",
- " <td>Western Europe</td>\n",
- " <td>5</td>\n",
- " <td>7.413</td>\n",
- " <td>7.351</td>\n",
- " <td>7.475</td>\n",
- " <td>1.40598</td>\n",
- " <td>1.13464</td>\n",
- " <td>0.81091</td>\n",
- " <td>0.57104</td>\n",
- " <td>0.41004</td>\n",
- " <td>0.25492</td>\n",
- " <td>2.82596</td>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "</div>"
- ],
- "text/plain": [
- " Country Region Happiness Rank Happiness Score \\\n",
- "0 Denmark Western Europe 1 7.526 \n",
- "1 Switzerland Western Europe 2 7.509 \n",
- "2 Iceland Western Europe 3 7.501 \n",
- "3 Norway Western Europe 4 7.498 \n",
- "4 Finland Western Europe 5 7.413 \n",
- "\n",
- " Lower Confidence Interval Upper Confidence Interval \\\n",
- "0 7.460 7.592 \n",
- "1 7.428 7.590 \n",
- "2 7.333 7.669 \n",
- "3 7.421 7.575 \n",
- "4 7.351 7.475 \n",
- "\n",
- " Economy (GDP per Capita) Family Health (Life Expectancy) Freedom \\\n",
- "0 1.44178 1.16374 0.79504 0.57941 \n",
- "1 1.52733 1.14524 0.86303 0.58557 \n",
- "2 1.42666 1.18326 0.86733 0.56624 \n",
- "3 1.57744 1.12690 0.79579 0.59609 \n",
- "4 1.40598 1.13464 0.81091 0.57104 \n",
- "\n",
- " Trust (Government Corruption) Generosity Dystopia Residual \n",
- "0 0.44453 0.36171 2.73939 \n",
- "1 0.41203 0.28083 2.69463 \n",
- "2 0.14975 0.47678 2.83137 \n",
- "3 0.35776 0.37895 2.66465 \n",
- "4 0.41004 0.25492 2.82596 "
- ]
- },
- "execution_count": 5,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "ha_df.head()"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "departmental-exhibition",
- "metadata": {},
- "source": [
- "## Do a boxplot showing the differences in `happiness` between `Region`:"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "saved-identity",
- "metadata": {},
- "outputs": [],
- "source": [
- "sns.boxplot(data=ha_df, x=\"Happiness Score\", y=\"Region\")"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "portuguese-worse",
- "metadata": {},
- "source": [
- "## Using a histogram and continuous probability density curve, display the distribution of `Freedom` in the dataset"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "continuous-indian",
- "metadata": {},
- "outputs": [],
- "source": [
- "sns.histplot(data=ha_df, x=\"Freedom\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "understanding-vegetarian",
- "metadata": {},
- "outputs": [],
- "source": [
- "sns.histplot(data=ha_df, x=\"Freedom\", kde=True)"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "prepared-stephen",
- "metadata": {},
- "source": [
- "- Use a barplot to show the count of country per Region (see the documentation for a countplot)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "worldwide-communication",
- "metadata": {},
- "outputs": [],
- "source": [
- "sns.countplot(data=ha_df, x=\"Region\")"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "4e1d16f2-57d8-4f0e-9a69-e9ab193a3ebc",
- "metadata": {},
- "source": [
- "As you can see the labels overlaps each ohers and are not readable\n",
- "\n",
- "One possibility is to rotate the X-labels. In this case is better to provide the labels."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "64ee74bb-5f37-485f-8c03-d06ac14d3010",
- "metadata": {},
- "outputs": [],
- "source": [
- "# extract the Region from the data, I will use them as labels for figures below\n",
- "regions = ha_df.loc[:, 'Region'].drop_duplicates()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "eb7c96ac-585a-4787-a2ee-dec3d04790ca",
- "metadata": {},
- "outputs": [],
- "source": [
- "ax = sns.countplot(data=ha_df, x=\"Region\")\n",
- "ax.set_xticks(regions)\n",
- "ax.set_xticklabels(regions, rotation=45, ha='right', rotation_mode='anchor')"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "e2eac27c-2de9-4942-82b9-294318ec5fd4",
- "metadata": {},
- "source": [
- "## On the same data `Happiness` and `Region` do a boxplot and a swarmplot to display the structure of the data"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "b0fd6058-65b0-4f9b-bc59-dce0193f1580",
- "metadata": {},
- "outputs": [],
- "source": [
- "ax = sns.swarmplot(data=ha_df, x=\"Region\", y=\"Happiness Score\")\n",
- "ax.set_xticks(regions)\n",
- "ax.set_xticklabels(regions,rotation=45, ha='right', rotation_mode='anchor')"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "1fe079b4-013a-4d48-ac31-9daad4b4673e",
- "metadata": {},
- "outputs": [],
- "source": [
- "ax = sns.boxplot(data=ha_df, x=\"Region\", y=\"Happiness Score\", hue='Region') # see the result of the option hue\n",
- "ax.set_xticks(regions)\n",
- "ax.set_xticklabels(regions,rotation=45, ha='right', rotation_mode='anchor')"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "immediate-method",
- "metadata": {},
- "source": [
- "## Plot the distribution of `happiness` for the people leaving `Western Europe`"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "academic-measure",
- "metadata": {},
- "outputs": [],
- "source": [
- "sns.histplot(data=ha_df.query(\"Region == 'Western Europe'\"), x=\"Happiness Score\", kde=True)"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "fd9789db-9bab-478a-bcec-1c8b6775cf20",
- "metadata": {},
- "source": [
- "## Plot the `Health (Life Expectancy)` vs `Happiness Score` and color the dots according to the region "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "d42f72f1-1d01-496e-89a1-68391ffa4281",
- "metadata": {},
- "outputs": [],
- "source": [
- "import matplotlib.pyplot as plt"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "52ae8376-3c66-4ca6-86a9-f9ae9f56076f",
- "metadata": {},
- "outputs": [],
- "source": [
- "fig, ax = plt.subplots(figsize=(9, 7))\n",
- "sns.scatterplot(data=ha_df, x=\"Health (Life Expectancy)\", y=\"Happiness Score\", hue=\"Region\", ax=ax)"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "temporal-synthesis",
- "metadata": {},
- "source": [
- "- Feel free to explore more of [seaborn](https://seaborn.pydata.org/examples/index.html) !"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "3063abf7-2251-48eb-b371-6c5b70b45fe7",
- "metadata": {},
- "source": [
- "## Do a barplot of the Happiness Score for each Region"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "85dd0df6-74e7-43be-9a7c-eb922a06601b",
- "metadata": {},
- "outputs": [],
- "source": [
- "sns.barplot(data=ha_df, y=\"Region\", x=\"Happiness Score\", hue='Region', orient='h')"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "3ee5741a-64f4-4690-963b-1f7e729398bf",
- "metadata": {},
- "source": [
- "## from this point we will focus on the Regions\n",
- "\n",
- "### clean our dataset. Remove not relevant columns"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "0344b730-1535-47fb-82f5-07003fd223f9",
- "metadata": {},
- "outputs": [],
- "source": [
- "ha_df.columns"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "36e449d1-0add-4ebc-8903-d535219ce423",
- "metadata": {},
- "source": [
- "1. keep only columns 'Region', 'Happiness Score', 'Economy (GDP per Capita)', 'Family', 'Freedom','Trust (Government Corruption)', 'Generosity'\n",
- "2. set the index to the Region\n",
- "3. have a look on your new data"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "bdf897c4-b8f3-4dff-b9c0-0ad47b25ecc0",
- "metadata": {},
- "outputs": [],
- "source": [
- "region_df = ha_df.loc[:, ['Region', 'Happiness Score', 'Economy (GDP per Capita)', 'Family', 'Freedom','Trust (Government Corruption)', 'Generosity']]\n",
- "region_df.set_index('Region', inplace=True)\n",
- "region_df.head()"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "e1ae03ac-ac7c-436d-987d-113e9cca3eec",
- "metadata": {},
- "source": [
- "## Aggregate the new data region by region. Compute the mean of each country as value for the corresponding Region"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "3fc3ea89-a448-4e7b-abfb-3fa92cffc5f7",
- "metadata": {},
- "outputs": [],
- "source": [
- "reg_agg = region_df.groupby('Region').agg('mean')\n",
- "reg_agg"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "97cb188c-3e50-4492-961f-cadea3611aaa",
- "metadata": {},
- "source": [
- "## Do a hierarchically-clustered heatmap "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "9aa21ed4-e9b2-4eb3-a693-c59ceb513552",
- "metadata": {},
- "outputs": [],
- "source": [
- "sns.clustermap(data=reg_agg)"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "88d27d29-e3b8-43d7-8324-25e50c247872",
- "metadata": {},
- "source": [
- "Check the data."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "0128f575-0b2a-4cbc-8f6e-8b7e22d81254",
- "metadata": {},
- "outputs": [],
- "source": [
- "reg_agg.describe()"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "f9b39ab8-0051-4840-9e87-fe2bcb8ca07a",
- "metadata": {},
- "source": [
- "The data are not in the same range, so it could be better to standardize the data before to do the clustering"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "ff4beb57-b357-47a3-b7bd-877e05229b6b",
- "metadata": {},
- "outputs": [],
- "source": [
- "normalized_reg=(reg_agg - reg_agg.mean()) / reg_agg.std()\n",
- "normalized_reg"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "e19f9472-cb9b-434b-8689-2bf09d49b902",
- "metadata": {},
- "outputs": [],
- "source": [
- "sns.clustermap(data=normalized_reg, annot=True) # see the results of the annot option "
- ]
- },
- {
- "cell_type": "markdown",
- "id": "d64a0377-339b-4fe7-beb4-a32e4a4e0113",
- "metadata": {},
- "source": [
- "It's possible to do that directly in seaborn. with the option z_score (https://seaborn.pydata.org/generated/seaborn.clustermap.html)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "3b439517-5007-4fbb-828d-265f9835594f",
- "metadata": {},
- "outputs": [],
- "source": [
- "sns.clustermap(data=reg_agg, z_score=1, annot=True)"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "f8d6188e-3a37-4ba5-b377-a11696054e9c",
- "metadata": {},
- "source": [
- "- Explore the clustermap documentation to have a more visual heatmap by standardizing the data within genes."
- ]
- },
- {
- "cell_type": "markdown",
- "id": "a2627322-e6a5-422f-8a69-b89dbd4b777e",
- "metadata": {},
- "source": [
- "## Create a function which produce a single image with four different plots of your choice and save it to pdf file.\n",
- "\n",
- "like the image below."
- ]
- },
- {
- "cell_type": "markdown",
- "id": "4121ff3d-6814-493e-a505-357ad81b0d28",
- "metadata": {},
- "source": [
- "<img src=\"../images/multiple_figure.png\" width=\"50%\" />"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "a322c866-9232-4fae-bcee-9a635e3fd70b",
- "metadata": {},
- "outputs": [],
- "source": [
- "import matplotlib.pyplot as plt"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "044022d1-741d-4a07-ba7f-c1f863cca138",
- "metadata": {},
- "outputs": [],
- "source": [
- "def expression_graph():\n",
- " fig, axs = plt.subplots(2,2, figsize=(9,7), constrained_layout=True) # constrained_layout=True avoid overlapping between axis title and X-labels from the above figure\n",
- " sns.boxplot(data=ha_df, x=\"Happiness Score\", y=\"Region\", hue='Region', ax=axs[0,0])\n",
- " axs[0,0].set_title(\"happiness data structure\")\n",
- " \n",
- " sns.scatterplot(data=ha_df, x=\"Health (Life Expectancy)\", y=\"Happiness Score\", hue=\"Region\", legend=False, ax=axs[0,1])\n",
- " axs[0,1].set_title(\"Happiness vs Health\")\n",
- " \n",
- " sns.barplot(data=ha_df, y=\"Region\", x=\"Happiness Score\", hue='Region', orient='h', ax=axs[1,0])\n",
- " axs[1,0].set_title(\"happiness through the world\")\n",
- " \n",
- " sns.histplot(data=ha_df, x=\"Happiness Score\", kde=True, ax=axs[1,1])\n",
- " axs[1,1].set_title(\"Happiness data distribution\")\n",
- " \n",
- " return fig\n",
- " "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "c33bfc78-7480-4327-93a0-f8aaca0d3614",
- "metadata": {},
- "outputs": [],
- "source": [
- "my_fig = expression_graph()\n",
- "my_fig.suptitle(\"Happiness Report\")\n",
- "my_fig.savefig(\"happiness_visualization.pdf\", bbox_inches = \"tight\") # bbox_inches = \"tight\" avoid to truncate the Y-labels on left on pdf"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "0d05aba4-3c85-4cd9-85f3-5296b19308fb",
- "metadata": {},
- "source": [
- "# Extras"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "66d6668e-683f-462e-a72f-28bdda8736f2",
- "metadata": {},
- "source": [
- "- Using ipywidget, make a function to display barplot of `Happiness Score` by country but with region selected by the user (using a Dropdown widget)"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "042bd87e-d2dc-4544-a771-51d80c565d0f",
- "metadata": {},
- "source": [
- "Imports the needed modules \n",
- "- `widgets` and `interact` from the `ipywidgets` package\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "64ebeca1-1332-4585-9e5c-c1b66f82be71",
- "metadata": {},
- "outputs": [],
- "source": [
- "from ipywidgets import widgets\n",
- "from ipywidgets import interact"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "277264e6-a173-40c5-b71e-4cd551a7fa99",
- "metadata": {},
- "source": [
- "create a dataframe containing regions (without duplicates values"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "ebf7fde9-b4a1-4e8a-86ab-86ad8b1b533a",
- "metadata": {},
- "outputs": [],
- "source": [
- "regions = ha_df.loc[:, 'Region'].drop_duplicates()"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "f34e5053-ccf5-4a67-96db-7457fe16bbd6",
- "metadata": {},
- "source": [
- "1. Use this DataFarame to populate your dropdown list\n",
- "2. Use the region selected in dropdown list as parameter of your function\n",
- "3. select form the whole data frame the data corresponding to this region\n",
- "4. display the barplot"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "feba608f-2ecb-41ae-b04a-12f075fd644b",
- "metadata": {},
- "source": [
- "below the code skeleton of your function\n",
- "\n",
- "```python\n",
- "@interact(region=widgets.Dropdown(options=regions))\n",
- "def plot_counts(region):\n",
- " data = ha_df.loc[ha_df['Region'] == region]\n",
- " ax = sns.barplot(data= ....\n",
- "```"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "fb746fda-36cc-4c35-92d8-257a489fb278",
- "metadata": {},
- "outputs": [],
- "source": [
- "\n",
- "@interact(region=widgets.Dropdown(options=regions))\n",
- "def plot_counts(region):\n",
- " data = ha_df.loc[ha_df['Region'] == region]\n",
- " ax = sns.barplot(data=data, y='Happiness Score', x='Country')\n",
- " ax.set_xticks(data.Country)\n",
- " ax.set_xticklabels(data.Country, rotation=45, ha='right', rotation_mode='anchor')\n",
- " "
- ]
- },
- {
- "cell_type": "markdown",
- "id": "3f4bd68e-eb26-46f8-a00f-86f9d0570580",
- "metadata": {},
- "source": [
- "You can customize your figure as classical seaborn/matplotib figure\n",
- "\n",
- "for instance to display the value above each bar"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "7bcee7c5-f1c2-4035-9b7c-e68e1d73a932",
- "metadata": {},
- "outputs": [],
- "source": [
- "\n",
- "@interact(region=widgets.Dropdown(options=regions))\n",
- "def plot_counts(region):\n",
- " data = ha_df.loc[ha_df['Region'] == region]\n",
- " ax = sns.barplot(data=data, y='Happiness Score', x='Country')\n",
- " for i in ax.containers:\n",
- " # add label on each bar https://www.geeksforgeeks.org/how-to-show-values-on-seaborn-barplot/\n",
- " ax.bar_label(i, fmt=\"{:.2f}\", rotation='vertical', padding=3)\n",
- " \n",
- " ax.set_xticks(data.Country)\n",
- " ax.set_xticklabels(data.Country, rotation=45, ha='right', rotation_mode='anchor')\n",
- " ax.margins(y=0.1) # add margin to avoid to have label outside the barplotboundaries, here add 10% white space vertically \n",
- " # https://stackoverflow.com/questions/72662991/how-can-i-prevent-bar-labels-from-going-outside-the-barplot-boundaries-range\n",
- " "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "d78b7b86-ecaa-4d27-80ca-2d3e46c2aca3",
- "metadata": {},
- "outputs": [],
- "source": []
- }
- ],
- "metadata": {
- "kernelspec": {
- "display_name": "Python 3 (ipykernel)",
- "language": "python",
- "name": "python3"
- },
- "language_info": {
- "codemirror_mode": {
- "name": "ipython",
- "version": 3
- },
- "file_extension": ".py",
- "mimetype": "text/x-python",
- "name": "python",
- "nbconvert_exporter": "python",
- "pygments_lexer": "ipython3",
- "version": "3.11.10"
- }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}