Dodanie dockerfile

.gitignore

@@ -59,3 +59,4 @@ docs/source/changelog.md
 fifa19*
 *.csv
 stat.txt
+.venv/

Dockerfile

@@ -0,0 +1,10 @@
+FROM ubuntu:latest
+RUN apt update && apt install -y python3.8 && apt install -y python3-pip
+
+WORKDIR /app
+
+COPY ["requirements.txt", "./"]
+RUN pip3 install -r requirements.txt
+
+COPY ["Zadanie 1.py", "."]
+CMD python3.8 "Zadanie 1.py"

Jenkinsfile

@@ -42,3 +42,5 @@ pipeline {
         }
     }
 }
+
+//docker run  -e KAGGLE_KEY -e KAGGLE_USERNAME -ti ium_434760:latest

README.md

@@ -1,2 +1,3 @@
 # ium_434760
-
+## Uruchomienie 
+docker run  -e KAGGLE_KEY -e KAGGLE_USERNAME -ti adnovac/ium_s434760:latest

Zadanie 1.ipynb

@@ -45,7 +45,9 @@
   {
    "cell_type": "code",
    "execution_count": 208,
-   "metadata": {},
+   "metadata": {
+    "scrolled": true
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -78,6 +80,8 @@
    "outputs": [],
    "source": [
     "import zipfile\n",
+    "import pandas as pd\n",
+    "from sklearn.model_selection import train_test_split\n",
     "\n",
     "with zipfile.ZipFile('fifa19.zip', 'r') as zip_ref:\n",
     "    zip_ref.extractall('.')"
@@ -136,8 +140,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
+    "\n",
-    "from sklearn.model_selection import train_test_split\n",
     "\n",
     "df=pd.read_csv('data.csv')\n",
     "train, dev = train_test_split(df, train_size=0.6, test_size=0.4, shuffle=True)\n",

Zadanie 1.py

@@ -0,0 +1,35 @@
+import zipfile
+import os
+import pandas as pd
+from sklearn.model_selection import train_test_split
+
+if os.getenv("KAGGLE_KEY") is None or os.getenv("KAGGLE_USERNAME") is None:
+    print("Brak zmiennych środowiskowych KAGGLE_KEY lub KAAGLE_USERNAME")
+    exit()
+
+if not os.path.isfile('fifa19.zip'):
+    os.system('kaggle datasets download -d karangadiya/fifa19')
+
+with zipfile.ZipFile('fifa19.zip', 'r') as zip_ref:
+    zip_ref.extractall('.')
+
+df=pd.read_csv('data.csv')
+df = df[df["Release Clause"].notna()]
+df = df[df["Release Clause"].notnull()]
+
+if df["Overall"].mean() > 1:
+    df["Overall"]= df["Overall"]/100
+
+df["Release Clause"] = df["Release Clause"].str.replace("€", "")
+
+df["Release Clause"] = (df["Release Clause"].replace(r'[KM]+$', '', regex=True).astype(float) * 
+          df["Release Clause"].str.extract(r'[\d\.]+([KM]+)', expand=False)
+          .replace(['K','M'], [1000, 1000000]).astype(int))
+
+df.to_csv('data.csv')
+train, dev = train_test_split(df, train_size=0.6, test_size=0.4, shuffle=True)
+dev, test = train_test_split(dev,  train_size=0.5, test_size=0.5, shuffle=False)
+
+test.to_csv('test.csv') 
+dev.to_csv('dev.csv') 
+train.to_csv('train.csv')

requirements.txt

@@ -0,0 +1,4 @@
+kaggle
+pandas
+numpy
+sklearn