{"cells":[{"metadata":{},"cell_type":"markdown","source":"![melanoma.jpg](attachment:melanoma.jpg)\n\n- **Melanoma is the deadliest form of skin cancer**. It occurs when pigment-making cells in the skin, called melanocytes, begin to reproduce uncontrollably. Melanoma can form from an existing mole or develop on unblemished skin.\n\n- The most common type of melanoma spreads on the skin's surface. It is called superficial spreading melanoma. It may stay on the surface or grow down into deeper tissues. Other types of melanoma can start anywhere on or inside the body, including under fingernails or toenails and inside the eye.\n\n- Melanoma rarely occurs before age 18. However, the risk of melanoma rises rapidly in young adulthood, making it one of the most common **life-threatening forms of cancer in people between the ages of 20 and 50.** After age 50, the risk of melanoma rises more slowly with advancing age.\n\n- Source: [Melanoma - Harvard  Health](https://www.health.harvard.edu/cancer/melanoma-overview)","attachments":{"melanoma.jpg":{"image/jpeg":"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"}},"execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## Importing Libraries","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport missingno as msno\nfrom plotly.offline import iplot, init_notebook_mode\ninit_notebook_mode()\nimport plotly.graph_objs as go\nimport plotly.express as px\nimport seaborn as sns\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/siim-isic-melanoma-classification/train.csv')\ntest = pd.read_csv('../input/siim-isic-melanoma-classification/test.csv')\nsample_sub = pd.read_csv('../input/siim-isic-melanoma-classification/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_sub.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('Train has {:,} rows and Test has {:,} rows.'.format(len(train), len(test)))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Renaming the columns:","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"cols = ['image', 'ID', 'sex', 'age', 'anatomy_site', 'diagnosis', 'benign_malignant', 'target']\ntrain.columns = cols\ntest.columns = cols[:5]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"print(train.columns)\nprint(test.columns)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Missing Values","execution_count":null},{"metadata":{"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"print(train.isnull().sum())\nprint(test.isnull().sum())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# msno.bar(train)\n\nplt.style.use('seaborn-colorblind')\nf, (ax1, ax2) = plt.subplots(1, 2, figsize = (16, 6))\n\nmsno.bar(train, ax = ax1, color=(193/255, 53/255, 192/255), fontsize=10)\nmsno.bar(test, ax = ax2, color=(251/255, 0/255, 0/255), fontsize=10)\n\nax1.set_title('Train Missing Values Map', fontsize = 16)\nax2.set_title('Test Missing Values Map', fontsize = 16);","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Missing Values in Training Data.\n\n- **sex : 65**\n- **age : 68**\n- **anatomy_site : 527**\n","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"print(plt.style.available)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.style.use('seaborn-colorblind')\nf, (ax1, ax2) = plt.subplots(1, 2, figsize = (15, 5))\n\nmsno.matrix(train, ax = ax1, color=(0/255, 248/255, 0/255), fontsize=10 ,sparkline=False)\nmsno.matrix(test, ax = ax2, color=(0/255, 0/255, 220/255), fontsize=10 ,sparkline=False)\n\nax1.set_title('Missing Values in Training Data', fontsize = 16)\nax2.set_title('Missing Value in Testing Data', fontsize = 16);","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Missing Values in Test Data:\n\n- **anatom_site : 351**\n","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# msno.dendrogram(train)\n# plt.style.use('seaborn-notebook')\nf, (ax1, ax2) = plt.subplots(1, 2, figsize = (18, 5))\n\nmsno.dendrogram(train, ax = ax1, fontsize=12)\nmsno.dendrogram(test, ax = ax2, fontsize=12)\n\n# ax1.set_title('Train Missing Values Map', fontsize = 16)\n# ax2.set_title('Test Missing Values Map', fontsize = 16);\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Missing Values Imputation in Training Data:\n\n- **sex : 65/33126**\n- **age : 68/33126**\n- **anatomy_site : 527/33126**","execution_count":null},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"train.nunique()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"# train['anatomy_site'].value_counts().sort_index().plot.bar()\n\nprint(train['anatomy_site'].value_counts())\nprint(train['age'].value_counts())\nprint(train['sex'].value_counts())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# train['age'].value_counts().sort_index().plot.bar()\nplt.style.use('dark_background')\nplt.figure(figsize=(10,8))  \n# sns.set(style=\"darkgrid\")\nax = sns.countplot(x = train['age'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Age:\n\n- 45.0 :   4466\n\n- 50.0 :  4270\n\n- 55.0  : 3824\n\n- 40.0 : 3576\n\n- 60.0 :   3240\n\n- 35.0 :   2850\n\n- 65.0 :   2527\n\n- 30.0 :   2358\n\n- 70.0 :   1968\n\n- 25.0 :   1544\n\n- 75.0  :   981\n\n- 20.0  :   655\n\n- 80.0  :   419\n\n- 85.0  :   149\n\n- 15.0  :   132\n\n- 90.0      80\n\n- 10.0  :    17\n\n- 0.0   :     2","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"## Can use this as well to plot. \n# train['sex'].value_counts().sort_index().plot.bar()\n\n\n## Alternate and better plot:\n\n# plt.figure(figsize=(10,8))  \nsns.set(style=\"darkgrid\")\nplt.style.use('seaborn-notebook')\nax = sns.countplot(x = train['sex'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Sex:\n\n- **male --> 17080**\n\n- **female --> 15981**","execution_count":null},{"metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"print(plt.style.available)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(10,8))\nsns.set(style=\"darkgrid\")\nplt.style.use('seaborn-notebook')\nax = sns.countplot(y = train['anatomy_site'],facecolor=(0, 0, 0, 0),\n                   linewidth=5,\n                   edgecolor=sns.color_palette(\"dark\", 3))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Anatomy_site:\n\n- torso --> 16845\n\n- lower extremity --> 8417\n\n- upper extremity --> 4983\n\n- head/neck --> 1855\n\n- palms/soles --> 375\n\n- oral/genital  --> 124","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"f, (ax1, ax2) = plt.subplots(1, 2, figsize = (15, 5))\n\nsns.set(style=\"darkgrid\")\na = sns.countplot(x = train['anatomy_site'], ax = ax1)\nb = sns.countplot(x = test['anatomy_site'], ax = ax2)\n\na.set_xticklabels(a.get_xticklabels(), rotation=45, ha=\"right\")\nb.set_xticklabels(b.get_xticklabels(), rotation=45, ha=\"right\")\n\nax1.set_title('Anatomy Site Distribution in Training Data', fontsize = 16)\nax2.set_title('Anatomy Site Distribution in Testing Data', fontsize = 16);","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**In both Test and training data, 'torso' is the mode in anatomy_site column**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize = (10,8))\nplt.style.use('fivethirtyeight')\nax = sns.countplot(x= \"anatomy_site\", hue=\"sex\", data=train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.style.use('dark_background')\nplt.figure(figsize = (10,8))\nax = sns.countplot(x= \"sex\", hue= \"age\", data=train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize = (10,8))\nax = sns.countplot(x = \"target\", hue = \"sex\", data = train)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Haven't found any strong correlation between columns**\n- Let's impute the null values with:\n\n- **Age --> Median**\n- **Sex --> Mode**\n- **Anatomy_site --> Mode**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"train['age'].median()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['age'].fillna(50,inplace = True) \ntrain['sex'].fillna('male', inplace = True) \ntrain['anatomy_site'].fillna('torso', inplace = True) \ntest['anatomy_site'].fillna('torso', inplace = True)\n\nprint(train.isnull().sum())\nprint(test.isnull().sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## EDA: Let's do some Analysis.","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"**1. Target Variable** ","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train['target'].value_counts())\n\nplt.style.use('dark_background')\nplt.figure(figsize=(10,8))  \n# sns.set(style=\"darkgrid\")\nsns.countplot(x = train['target'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**32542 --> 0**\n\nand only\n**584 --> 1s**\n","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# x = dict(train['diagnosis'].value_counts())\n# print(x)\n# print(x.keys())\n\n\nplt.figure(figsize=(10,8))  \nsns.set(style=\"darkgrid\")\na = sns.countplot(x = train['diagnosis'])\na.set_xticklabels(a.get_xticklabels(), rotation=45, ha=\"right\")\n# b.set_xticklabels(b.get_xticklabels(), rotation=35, ha=\"right\")\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Handling Class Imbalance:","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"![under-over.png](attachment:under-over.png)\n\n**Oversampling** and **undersampling** in data analysis are techniques used to adjust the class distribution of a data set (i.e. the ratio between the different classes/categories represented). These terms are used both in statistical sampling, survey design methodology and in machine learning.\n\nOversampling and undersampling are opposite and roughly equivalent techniques.\n\n**In simple Terms**\n\n- Undersampling does undersamples the training data so that both the classes have equal distribution.\n\n- Oversampling is oversamples the training data so that both the classes have equal distribution.","attachments":{"under-over.png":{"image/png":"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"}},"execution_count":null},{"metadata":{},"cell_type":"markdown","source":"### 1. [Undersampling:](https://imbalanced-learn.readthedocs.io/en/stable/generated/imblearn.under_sampling.NearMiss.html)","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"y = train['target']\nplt.style.use('dark_background')\n# plt.style.use('seaborn-paper')\na = y.value_counts().plot.bar()\na.set_xticklabels(a.get_xticklabels(), rotation=0, ha=\"right\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder\n\n# Drop the unwanted columns\ntrain = train.drop(['image','ID','diagnosis','benign_malignant'],axis=1)\n\n# Label Encode categorical features\ntrain['age'].fillna(50,inplace = True) \ntrain['sex'].fillna('male', inplace = True) \ntrain['anatomy_site'].fillna('torso', inplace = True) \n\nle_sex = LabelEncoder()\nle_site = LabelEncoder()\ntrain.sex = le_sex.fit_transform(train.sex)\n\n## Getting dummies for anatomy_site\nx = pd.get_dummies(train['anatomy_site'], drop_first = True)\n\n## Concat dummies and actual data.\ntrain_x = pd.concat([train,x], axis = 1)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_x.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from imblearn.under_sampling import NearMiss\n\nX = train_x.drop(['target','anatomy_site'], axis = 1)\nn = NearMiss()\nX_new,y_new = n.fit_sample(X,y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.style.use('dark_background')\n# plt.style.use('seaborn-paper')\na = y_new.value_counts().plot.bar()\na.set_xticklabels(a.get_xticklabels(), rotation=0, ha=\"right\")","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Both Ones and Zeroes are 584**. This is known as balanced dataset, but the issue here is we have reduced the dataset drastically. ","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"### 2. [Oversampling:](https://imbalanced-learn.readthedocs.io/en/stable/generated/imblearn.combine.SMOTETomek.html)","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"from imblearn.combine import SMOTETomek\nsmk = SMOTETomek(random_state=42)\nX_new_over,y_new_over = smk.fit_sample(X,y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.style.use('dark_background')\n# plt.style.use('seaborn-paper')\na = y_new_over.value_counts().plot.bar()\na.set_xticklabels(a.get_xticklabels(), rotation=0, ha=\"right\")","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Now the sample size is north of 30K.**","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## Next Steps:\n\n- Feature Extraction\n\n- Modelling\n\n- Predictions\n\n","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## References\n\n1. [SIIM Melanoma Competition: EDA + Augmentations](https://www.kaggle.com/andradaolteanu/siim-melanoma-competition-eda-augmentations)\n\n2. [Missingno Github Repository](https://github.com/ResidentMario/missingno)\n\n3. [Seaborn Countplot](https://seaborn.pydata.org/generated/seaborn.countplot.html)\n\n4. [Cover Image Source](https://www.health.harvard.edu/cancer/melanoma-overview)\n\n5. [Matplotlib Visualizations](https://matplotlib.org/3.2.2/tutorials/introductory/customizing.html)\n\n6. [imblearn.under_sampling.NearMiss](https://imbalanced-learn.readthedocs.io/en/stable/generated/imblearn.under_sampling.NearMiss.html)\n\n7. [imblearn.combine.SMOTETomek](https://imbalanced-learn.readthedocs.io/en/stable/generated/imblearn.combine.SMOTETomek.html)\n\n","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"**Feel free to fork and if you find this kernel helpful do cast an upvote.**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}