Skip to content

Commit 4a91604

Browse files
bcopybcopy
committed
Comment out code samples
1 parent 265aab0 commit 4a91604

1 file changed

Lines changed: 77 additions & 64 deletions

File tree

‎content/titanic/Případová_studie_-_Titanic-řešení.ipynb‎

Lines changed: 77 additions & 64 deletions
Original file line numberDiff line numberDiff line change
@@ -272,8 +272,8 @@
272272
}
273273
],
274274
"source": [
275-
"df_titanic = pd.read_csv('titanic.csv')\n",
276-
"df_titanic.head()"
275+
"# df_titanic = pd.read_csv('titanic.csv')\n",
276+
"# df_titanic.head()"
277277
]
278278
},
279279
{
@@ -328,7 +328,7 @@
328328
}
329329
],
330330
"source": [
331-
"df_titanic.info()"
331+
"# df_titanic.info()"
332332
]
333333
},
334334
{
@@ -360,8 +360,8 @@
360360
}
361361
],
362362
"source": [
363-
"#Další způsob, jak zobrazit počet chybějících hodnot v každém sloupci\n",
364-
"df_titanic.isnull().sum()"
363+
"# Další způsob, jak zobrazit počet chybějících hodnot v každém sloupci\n",
364+
"#df_titanic.isnull().sum()"
365365
]
366366
},
367367
{
@@ -524,9 +524,10 @@
524524
],
525525
"source": [
526526
"# uklidit Fare, převést na float\n",
527-
"df_titanic.Fare = df_titanic.Fare.str.replace('$','')\n",
528-
"df_titanic['Fare'] = df_titanic.Fare.astype(float)\n",
529-
"df_titanic.head()"
527+
"\n",
528+
"# df_titanic.Fare = df_titanic.Fare.str.replace('$','')\n",
529+
"# df_titanic['Fare'] = df_titanic.Fare.astype(float)\n",
530+
"# df_titanic.head()"
530531
]
531532
},
532533
{
@@ -692,7 +693,7 @@
692693
}
693694
],
694695
"source": [
695-
"df_titanic.describe()"
696+
"# df_titanic.describe()"
696697
]
697698
},
698699
{
@@ -754,11 +755,12 @@
754755
],
755756
"source": [
756757
"# Kolik jich přežilo\n",
757-
"f,ax=plt.subplots(figsize=(5,5))\n",
758-
"sns.countplot(x='Survived',data=df_titanic, ax = ax)\n",
759-
"ax.set_title('Zahynulí vs. přežili')\n",
760-
"# Není nutné, jen k odstranění jakéhokoli výstupu\n",
761-
"plt.show()"
758+
"\n",
759+
"# f,ax=plt.subplots(figsize=(5,5))\n",
760+
"# sns.countplot(x='Survived',data=df_titanic, ax = ax)\n",
761+
"# ax.set_title('Zahynulí vs. přežili')\n",
762+
"\n",
763+
"# plt.show()"
762764
]
763765
},
764766
{
@@ -781,11 +783,12 @@
781783
],
782784
"source": [
783785
"# počet přeživších\n",
784-
"f,ax=plt.subplots(figsize=(5,5))\n",
785-
"přeživší_počet = df_titanic.Survived.value_counts()\n",
786-
"přeživší_počet.plot.bar(ax=ax)\n",
787-
"ax.set_title('Zahynulí vs. přežili')\n",
788-
"plt.show()"
786+
"\n",
787+
"# f,ax=plt.subplots(figsize=(5,5))\n",
788+
"# přeživší_počet = df_titanic.Survived.value_counts()\n",
789+
"# přeživší_počet.plot.bar(ax=ax)\n",
790+
"# ax.set_title('Zahynulí vs. přežili')\n",
791+
"# plt.show()"
789792
]
790793
},
791794
{
@@ -808,12 +811,13 @@
808811
],
809812
"source": [
810813
"# Procento přeživších počet (survivorCount)\n",
811-
"f,ax=plt.subplots(figsize=(5,5))\n",
812-
"survivorCount = df_titanic.Survived.value_counts(normalize=True)\n",
813-
"survivorCount.plot.bar(ax=ax)\n",
814-
"ax.set_title('Zahynulí vs. přežili')\n",
815-
"ax.set_xticklabels( ['Zhynulo', 'Přežilo'], rotation=0)\n",
816-
"plt.show()"
814+
"\n",
815+
"# f,ax=plt.subplots(figsize=(5,5))\n",
816+
"# survivorCount = df_titanic.Survived.value_counts(normalize=True)\n",
817+
"# survivorCount.plot.bar(ax=ax)\n",
818+
"# ax.set_title('Zahynulí vs. přežili')\n",
819+
"# ax.set_xticklabels( ['Zhynulo', 'Přežilo'], rotation=0)\n",
820+
"# plt.show()"
817821
]
818822
},
819823
{
@@ -857,10 +861,11 @@
857861
],
858862
"source": [
859863
"# Muž vs. Žena\n",
860-
"f,ax=plt.subplots(figsize=(5,5))\n",
861-
"sns.countplot(x='Sex',data=df_titanic,ax=ax)\n",
862-
"ax.set_title('Muž vs. Žena')\n",
863-
"plt.show()"
864+
"\n",
865+
"# f,ax=plt.subplots(figsize=(5,5))\n",
866+
"# sns.countplot(x='Sex',data=df_titanic,ax=ax)\n",
867+
"# ax.set_title('Muž vs. Žena')\n",
868+
"# plt.show()"
864869
]
865870
},
866871
{
@@ -928,7 +933,8 @@
928933
],
929934
"source": [
930935
"# míra přežití žen/mužů\n",
931-
"df_titanic.groupby(['Sex'], as_index=False).agg({'Survived':'mean'})"
936+
"\n",
937+
"# df_titanic.groupby(['Sex'], as_index=False).agg({'Survived':'mean'})"
932938
]
933939
},
934940
{
@@ -961,10 +967,11 @@
961967
],
962968
"source": [
963969
"#Zhynul vs. přežil pro muže/ženu\n",
964-
"f,ax=plt.subplots(figsize=(5,5))\n",
965-
"sns.countplot(x='Sex',hue='Survived',data=df_titanic,ax=ax)\n",
966-
"ax.set_title('Pohlaví: Zahynulý vs. Přežil')\n",
967-
"plt.show()"
970+
"\n",
971+
"# f,ax=plt.subplots(figsize=(5,5))\n",
972+
"# sns.countplot(x='Sex',hue='Survived',data=df_titanic,ax=ax)\n",
973+
"# ax.set_title('Pohlaví: Zahynulý vs. Přežil')\n",
974+
"# plt.show()"
968975
]
969976
},
970977
{
@@ -1045,7 +1052,7 @@
10451052
}
10461053
],
10471054
"source": [
1048-
"df_titanic.groupby(['Pclass'], as_index=False).agg({'Survived':'mean'})"
1055+
"# df_titanic.groupby(['Pclass'], as_index=False).agg({'Survived':'mean'})"
10491056
]
10501057
},
10511058
{
@@ -1077,10 +1084,11 @@
10771084
],
10781085
"source": [
10791086
"# barový pozemek a seaborn počítat spiknutí\n",
1080-
"f,ax=plt.subplots(figsize=(5,5))\n",
1081-
"sns.countplot(x='Pclass',hue='Survived',data=df_titanic,ax=ax)\n",
1082-
"ax.set_title('Pclass: Zahynulý vs. Přežil')\n",
1083-
"plt.show()"
1087+
"\n",
1088+
"# f,ax=plt.subplots(figsize=(5,5))\n",
1089+
"# sns.countplot(x='Pclass',hue='Survived',data=df_titanic,ax=ax)\n",
1090+
"# ax.set_title('Pclass: Zahynulý vs. Přežil')\n",
1091+
"# plt.show()"
10841092
]
10851093
},
10861094
{
@@ -1139,8 +1147,9 @@
11391147
],
11401148
"source": [
11411149
"# použít dataframe hist(), který bude standardně zpracovávat NaN\n",
1142-
"obr, ax = plt.subplots()\n",
1143-
"df_titanic.Age.hist(ax=ax, bins=20, edgecolor='black', alpha=0.5)"
1150+
"\n",
1151+
"# obr, ax = plt.subplots()\n",
1152+
"# df_titanic.Age.hist(ax=ax, bins=20, edgecolor='black', alpha=0.5)"
11441153
]
11451154
},
11461155
{
@@ -1183,12 +1192,13 @@
11831192
],
11841193
"source": [
11851194
"# dataframe.hist(), který bude standardně zpracovávat NaN\n",
1186-
"obr, ax = plt.subplots()\n",
1187-
"df_titanic.Age.hist(ax=ax, label='all', bins=20, edgecolor='black', alpha=0.5)\n",
1188-
"# stack přežil\n",
1189-
"df_titanic[df_titanic.Survived==1].Age.hist(ax=ax, bins=20, color='g', label='survived', edgecolor='black', alpha=0.5)\n",
1190-
"ax.set_title('Věková distribuce')\n",
1191-
"ax.legend()"
1195+
"\n",
1196+
"# obr, ax = plt.subplots()\n",
1197+
"# df_titanic.Age.hist(ax=ax, label='all', bins=20, edgecolor='black', alpha=0.5)\n",
1198+
"# # stack přežil\n",
1199+
"# df_titanic[df_titanic.Survived==1].Age.hist(ax=ax, bins=20, color='g', label='survived', edgecolor='black', alpha=0.5)\n",
1200+
"# ax.set_title('Věková distribuce')\n",
1201+
"# ax.legend()"
11921202
]
11931203
},
11941204
{
@@ -1239,8 +1249,9 @@
12391249
}
12401250
],
12411251
"source": [
1242-
"#check all missing data\n",
1243-
"df_titanic.isnull().sum()"
1252+
"# check all missing data\n",
1253+
"\n",
1254+
"# df_titanic.isnull().sum()"
12441255
]
12451256
},
12461257
{
@@ -1292,8 +1303,9 @@
12921303
],
12931304
"source": [
12941305
"# naplnit NaN v Embarked s mode()\n",
1295-
"df_titanic['Embarked'].fillna(df_titanic.Embarked.mode()[0],inplace=True)\n",
1296-
"df_titanic.info()"
1306+
"\n",
1307+
"# df_titanic['Embarked'].fillna(df_titanic.Embarked.mode()[0],inplace=True)\n",
1308+
"# df_titanic.info()"
12971309
]
12981310
},
12991311
{
@@ -1469,8 +1481,9 @@
14691481
],
14701482
"source": [
14711483
"# extrahujte předponu z názvu\n",
1472-
"df_titanic['Title']=df_titanic.Name.str.extract('([A-Za-z]+\\.)')\n",
1473-
"df_titanic.head()"
1484+
"\n",
1485+
"# df_titanic['Title']=df_titanic.Name.str.extract('([A-Za-z]+\\.)')\n",
1486+
"# df_titanic.head()"
14741487
]
14751488
},
14761489
{
@@ -1638,8 +1651,8 @@
16381651
}
16391652
],
16401653
"source": [
1641-
"df_titanic.Title = df_titanic.Title.str.upper()\n",
1642-
"df_titanic.head()"
1654+
"# df_titanic.Title = df_titanic.Title.str.upper()\n",
1655+
"# df_titanic.head()"
16431656
]
16441657
},
16451658
{
@@ -1683,7 +1696,7 @@
16831696
}
16841697
],
16851698
"source": [
1686-
"df_titanic.Title.value_counts()"
1699+
"# df_titanic.Title.value_counts()"
16871700
]
16881701
},
16891702
{
@@ -1717,8 +1730,8 @@
17171730
}
17181731
],
17191732
"source": [
1720-
"df_titanic.Age.fillna(df_titanic.groupby('Title').Age.transform('mean'), inplace=True)\n",
1721-
"df_titanic.info()"
1733+
"# df_titanic.Age.fillna(df_titanic.groupby('Title').Age.transform('mean'), inplace=True)\n",
1734+
"# df_titanic.info()"
17221735
]
17231736
},
17241737
{
@@ -1869,7 +1882,7 @@
18691882
}
18701883
],
18711884
"source": [
1872-
"df_titanic[df_titanic.Name.str.contains('Asplund')]"
1885+
"# df_titanic[df_titanic.Name.str.contains('Asplund')]"
18731886
]
18741887
},
18751888
{
@@ -2043,8 +2056,8 @@
20432056
}
20442057
],
20452058
"source": [
2046-
"df_titanic['FamilySize'] = df_titanic.Parch + df_titanic.SibSp + 1\n",
2047-
"df_titanic.sample(5)"
2059+
"# df_titanic['FamilySize'] = df_titanic.Parch + df_titanic.SibSp + 1\n",
2060+
"# df_titanic.sample(5)"
20482061
]
20492062
},
20502063
{
@@ -2187,9 +2200,9 @@
21872200
}
21882201
],
21892202
"source": [
2190-
"import statsmodels.formula.api as smf\n",
2191-
"result = smf.ols(\"Fare ~ C(Pclass) + C(Embarked) + FamilySize\", data=df_titanic).fit()\n",
2192-
"result.summary()"
2203+
"# import statsmodels.formula.api as smf\n",
2204+
"# result = smf.ols(\"Fare ~ C(Pclass) + C(Embarked) + FamilySize\", data=df_titanic).fit()\n",
2205+
"# result.summary()"
21932206
]
21942207
}
21952208
],

0 commit comments

Comments
 (0)