mdk
/
formations
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Renaming without spaces.

This commit is contained in:
Julien Palard 2021-07-16 07:53:31 +02:00
parent b0f7dcb43d
commit 88233589f4
Signed by: mdk
GPG Key ID: 0EFC1AC1006886F8
4 changed files with 786 additions and 6513 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5351
python-initiation/Demo Jupyter.ipynb
View File

File diff suppressed because one or more lines are too long

1162
python-initiation/Pandas loc.ipynb
View File

File diff suppressed because it is too large Load Diff

565
python-initiation/demo-jupyter-numpy-pandas.ipynb Normal file
View File

@ -0,0 +1,565 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Demo Jupyter\n",
"\n",
"## Sous titre\n",
"\n",
"- une\n",
"- liste\n",
"- comme ça\n",
"\n",
"Les liens, [Ma page](https://mdk.fr)\n",
"\n",
"![titre de l'image](https://camo.githubusercontent.com/4cdea557cde90c6a18ded36cf1e51b0866f6ff4a/68747470733a2f2f6d646b2e66722f413133333035382e706e67)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import pandas as pd\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# import des données"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%matplotlib notebook\n",
"# %matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"a = np.array(range(10))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"a = np.zeros((4, 5))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"a"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"a[0, 0] = 5"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"a + 5"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"a * 2.5"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"1 + 1"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"np.arange(10, 20, .5)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"np.linspace(0, 100, 50)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"np.zeros((3, 3))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"np.zeros((3, 5))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"np.zeros((2, 3, 4, 5))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"b = np.random.rand(4, 4)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"np.random.rand(4, 4)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"b"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"b > 0.5"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"mask = b > .5"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"b[b < .5].mean()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"b[~mask]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"b[(b > .5) & (b < .7)]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iris = pd.read_excel('https://mdk.fr/iris.xls', index_col=0)\n",
"\n",
"# python -m pip install xlrd # Doit marcher\n",
"# py -m pip install xlrd # Doit marcher aussi !"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"type(iris)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iris.describe()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iris.loc"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iris.loc[3]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iris.loc[:4]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iris.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iris.loc[:3, \"sepal length (cm)\"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iris.loc[[2, 3, 4, 10], [\"sepal length (cm)\", \"petal length (cm)\"]]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iris.loc[0, \"sepal length (cm)\"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iris.loc[:, \"sepal length (cm)\"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"lengths = [colname for colname in iris.columns if \"length\" in colname]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iris.loc[:, lengths]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pd.read_csv"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pd.read_excel # Shift tab, Shift tab, Shift tab, Shift tab"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from pandas.plotting import scatter_matrix\n",
"plot = scatter_matrix(iris)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"x = np.linspace(0, 10, 100)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"x"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"y = np.sin(x)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"y"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"plot = plt.plot(x, y)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"noise = np.random.uniform(-1/10, 1/10, 100)\n",
"noise"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"plot = plt.plot(x, np.sin(x) + noise)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from matplotlib.colors import Normalize\n",
"\n",
"\n",
"def show(np_array):\n",
" fig, ax = plt.subplots(figsize=(9, np_array.shape[0]))\n",
" if len(np_array.shape) == 1:\n",
" np_array = [np_array]\n",
" for y, line in enumerate(np_array):\n",
" for x, value in enumerate(line):\n",
" offset = .1 if value < 10 else .2\n",
" ax.text(x - offset, y + .15, str(value), c=\"white\", fontsize=20)\n",
" ax.imshow(np_array, cmap=\"hsv\", norm=Normalize(1, 50), aspect='equal')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"a1 = np.arange(1, 13)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"show(a1)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"show(a1.reshape(2, 6))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"show(a1.reshape(6, 2))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"show(a1.reshape(3, 4).ravel())"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"a2 = np.arange(13, 25)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"show(a2)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"show(np.stack((a1, a2)))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"show(np.stack((a1, a2), axis=1))"
]
}
],
"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": "3.9.4"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

221
python-initiation/pandas.loc.ipynb Normal file
View File

@ -0,0 +1,221 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"random_matrix = np.random.rand(4, 3)\n",
"random_matrix"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame(random_matrix, columns=list(\"abc\"))\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df.loc[0] # Cross section"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df.loc[0, \"a\"] # Single item"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df.loc[0:3, \"a\":\"c\"] # Inclusive bounds!!"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df.loc[:, :] # Omitting start and end in X and omitting start and end in Y, gets everything"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df.loc[:, [\"a\", \"c\"]] # Listing column names instead of slicing"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df.loc[[0, 2], :] # Listing lines indexes instead of slicing"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df.loc[[0, 2], [\"a\", \"c\"]] # Specifying columns names and lines indices"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df.iloc[[0, 1], [0, 2]]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df.loc[[True, False, True, False]] # Applying a mask on indices"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df.loc[:, [True, False, True]] # Applying a mask over columns (Is it usefull??)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"mask = df[\"a\"] > .5 # Generating a mask\n",
"mask"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df[mask] # Applying a mask"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df[[\"a\", \"b\"]] = df[[\"b\", \"a\"]] # Swapping columns\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df.a # Works, too as an attribute"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df[\"d\"] = df[\"a\"] - df[\"a\"].mean() # Creates a new column by assigning a series to it\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df.loc[0] = {\"a\": 0, \"b\": 1, \"c\": 2, \"d\": 3} # Updates a row by assigning a dict to it\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"(df - df.mean()).loc[lambda df: df[\"a\"] > 0] # .loc also accepts df, easing chaining of functions."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df."
]
}
],
"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": "3.9.4"
}
},
"nbformat": 4,
"nbformat_minor": 2
}