TP1 : rappels Python
# =========================
# NUMPY — tableaux simples
# =========================
import numpy as np
# Création
a = np.array([1, 2, 3, 4])
b = np.arange(0, 10, 2) # [0,2,4,6,8]
c = np.linspace(0, 1, 5) # 5 valeurs entre 0 et 1
# Opérations de base
print(a + 2) # addition scalaire
print(a * 3) # multiplication
print(a + b[:4]) # opérations élément par élément
# Statistiques
print(a.mean(), a.std(), a.sum())
# Indexation
print(a[0], a[-1])
print(a[1:3])[3 4 5 6]
[ 3 6 9 12]
[ 1 4 7 10]
2.5 1.118033988749895 10
1 4
[2 3]
# =========================
# PANDAS — lecture & exploration CSV
# =========================
import pandas as pd
# Lecture CSV
df = pd.read_csv("https://github.com/pandas-dev/pandas/raw/main/doc/data/titanic.csv")
# Aperçu
print(df.head())
print(df.tail())
# Infos générales
print(df.info())
print(df.describe())
# Sélection de colonnes
print(df["Age"])
print(df[["Name", "Age"]])
# Filtrage
filtered = df[df["Age"] > 20]
print(filtered)
# Valeurs uniques
print(df["Embarked"].unique())
# Comptage
print(df["Cabin"].value_counts()) PassengerId Survived Pclass \
0 1 0 3
1 2 1 1
2 3 1 3
3 4 1 1
4 5 0 3
Name Sex Age SibSp \
0 Braund, Mr. Owen Harris male 22.0 1
1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1
2 Heikkinen, Miss Laina female 26.0 0
3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1
4 Allen, Mr. William Henry male 35.0 0
Parch Ticket Fare Cabin Embarked
0 0 A/5 21171 7.2500 NaN S
1 0 PC 17599 71.2833 C85 C
2 0 STON/O2. 3101282 7.9250 NaN S
3 0 113803 53.1000 C123 S
4 0 373450 8.0500 NaN S
PassengerId Survived Pclass Name \
886 887 0 2 Montvila, Rev. Juozas
887 888 1 1 Graham, Miss Margaret Edith
888 889 0 3 Johnston, Miss Catherine Helen "Carrie"
889 890 1 1 Behr, Mr. Karl Howell
890 891 0 3 Dooley, Mr. Patrick
Sex Age SibSp Parch Ticket Fare Cabin Embarked
886 male 27.0 0 0 211536 13.00 NaN S
887 female 19.0 0 0 112053 30.00 B42 S
888 female NaN 1 2 W./C. 6607 23.45 NaN S
889 male 26.0 0 0 111369 30.00 C148 C
890 male 32.0 0 0 370376 7.75 NaN Q
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 PassengerId 891 non-null int64
1 Survived 891 non-null int64
2 Pclass 891 non-null int64
3 Name 891 non-null object
4 Sex 891 non-null object
5 Age 714 non-null float64
6 SibSp 891 non-null int64
7 Parch 891 non-null int64
8 Ticket 891 non-null object
9 Fare 891 non-null float64
10 Cabin 204 non-null object
11 Embarked 889 non-null object
dtypes: float64(2), int64(5), object(5)
memory usage: 83.7+ KB
None
PassengerId Survived Pclass Age SibSp \
count 891.000000 891.000000 891.000000 714.000000 891.000000
mean 446.000000 0.383838 2.308642 29.699118 0.523008
std 257.353842 0.486592 0.836071 14.526497 1.102743
min 1.000000 0.000000 1.000000 0.420000 0.000000
25% 223.500000 0.000000 2.000000 20.125000 0.000000
50% 446.000000 0.000000 3.000000 28.000000 0.000000
75% 668.500000 1.000000 3.000000 38.000000 1.000000
max 891.000000 1.000000 3.000000 80.000000 8.000000
Parch Fare
count 891.000000 891.000000
mean 0.381594 32.204208
std 0.806057 49.693429
min 0.000000 0.000000
25% 0.000000 7.910400
50% 0.000000 14.454200
75% 0.000000 31.000000
max 6.000000 512.329200
0 22.0
1 38.0
2 26.0
3 35.0
4 35.0
...
886 27.0
887 19.0
888 NaN
889 26.0
890 32.0
Name: Age, Length: 891, dtype: float64
Name Age
0 Braund, Mr. Owen Harris 22.0
1 Cumings, Mrs. John Bradley (Florence Briggs Th... 38.0
2 Heikkinen, Miss Laina 26.0
3 Futrelle, Mrs. Jacques Heath (Lily May Peel) 35.0
4 Allen, Mr. William Henry 35.0
.. ... ...
886 Montvila, Rev. Juozas 27.0
887 Graham, Miss Margaret Edith 19.0
888 Johnston, Miss Catherine Helen "Carrie" NaN
889 Behr, Mr. Karl Howell 26.0
890 Dooley, Mr. Patrick 32.0
[891 rows x 2 columns]
PassengerId Survived Pclass \
0 1 0 3
1 2 1 1
2 3 1 3
3 4 1 1
4 5 0 3
.. ... ... ...
884 885 0 3
885 886 0 3
886 887 0 2
889 890 1 1
890 891 0 3
Name Sex Age SibSp \
0 Braund, Mr. Owen Harris male 22.0 1
1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1
2 Heikkinen, Miss Laina female 26.0 0
3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1
4 Allen, Mr. William Henry male 35.0 0
.. ... ... ... ...
884 Sutehall, Mr. Henry Jr male 25.0 0
885 Rice, Mrs. William (Margaret Norton) female 39.0 0
886 Montvila, Rev. Juozas male 27.0 0
889 Behr, Mr. Karl Howell male 26.0 0
890 Dooley, Mr. Patrick male 32.0 0
Parch Ticket Fare Cabin Embarked
0 0 A/5 21171 7.2500 NaN S
1 0 PC 17599 71.2833 C85 C
2 0 STON/O2. 3101282 7.9250 NaN S
3 0 113803 53.1000 C123 S
4 0 373450 8.0500 NaN S
.. ... ... ... ... ...
884 0 SOTON/OQ 392076 7.0500 NaN S
885 5 382652 29.1250 NaN Q
886 0 211536 13.0000 NaN S
889 0 111369 30.0000 C148 C
890 0 370376 7.7500 NaN Q
[535 rows x 12 columns]
['S' 'C' 'Q' nan]
Cabin
B96 B98 4
G6 4
C23 C25 C27 4
C22 C26 3
F33 3
..
E34 1
C7 1
C54 1
E36 1
C148 1
Name: count, Length: 147, dtype: int64
# =========================
# MATPLOTLIB — base
# =========================
import matplotlib.pyplot as plt
# Données
x = np.linspace(0, 10, 100)
y = np.sin(x)
# Graphique simple
plt.plot(x, y)
plt.title("Sinus")
plt.xlabel("x")
plt.ylabel("sin(x)")
plt.show()
# Scatter
plt.scatter(x, y)
plt.title("Scatter plot")
plt.show()
# Histogramme
plt.hist(np.random.randn(1000), bins=30)
plt.title("Histogram")
plt.show()
