{
"cells": [
{
"cell_type": "code",
"execution_count": 11,
"id": "0158ae9b",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import yfinance as yf\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.decomposition import PCA\n",
"from sklearn.cluster import KMeans\n",
"from sklearn.ensemble import IsolationForest\n",
"from sklearn.svm import OneClassSVM\n",
"from sklearn.metrics import silhouette_score\n",
"from datetime import datetime, timedelta\n",
"import warnings\n",
"warnings.filterwarnings('ignore')\n",
"\n",
"class CryptoAnalyzer:\n",
" def __init__(self):\n",
" # Top traded cryptocurrencies (using their Yahoo Finance tickers)\n",
" self.crypto_tickers = [\n",
" 'BTC-USD', 'ETH-USD', 'BNB-USD', 'XRP-USD', 'ADA-USD',\n",
" 'DOGE-USD', 'SOL-USD', 'DOT-USD', 'MATIC-USD', 'LTC-USD',\n",
" 'SHIB-USD', 'TRX-USD', 'AVAX-USD', 'UNI-USD', 'LINK-USD'\n",
" ]\n",
" self.data = {}\n",
" self.scaler = StandardScaler()\n",
" self.pca = PCA(n_components=2)\n",
" self.kmeans = None\n",
" self.isolation_forest = None\n",
" self.one_class_svm = None\n",
" \n",
" def download_data(self, period='1y', interval='1d'):\n",
" \"\"\"\n",
" Download historical price data for cryptocurrencies\n",
" \"\"\"\n",
" print(\"Downloading cryptocurrency data...\")\n",
" \n",
" for ticker in self.crypto_tickers:\n",
" try:\n",
" crypto_data = yf.download(ticker, period=period, interval=interval)\n",
" if not crypto_data.empty:\n",
" self.data[ticker] = crypto_data\n",
" print(f\"✓ Downloaded data for {ticker}\")\n",
" else:\n",
" print(f\"✗ No data for {ticker}\")\n",
" except Exception as e:\n",
" print(f\"✗ Error downloading {ticker}: {str(e)}\")\n",
" \n",
" print(f\"Successfully downloaded data for {len(self.data)} cryptocurrencies\\n\")\n",
" return self.data\n",
" \n",
" def preprocess_data(self):\n",
" \"\"\"\n",
" Preprocess the downloaded data for analysis\n",
" \"\"\"\n",
" print(\"Preprocessing data...\")\n",
" \n",
" # Create features for each cryptocurrency\n",
" features_list = []\n",
" returns_list = []\n",
" \n",
" for ticker, df in self.data.items():\n",
" try:\n",
" # Ensure we're working with single columns by selecting specific column names\n",
" if 'Close' in df.columns:\n",
" if isinstance(df['Close'], pd.DataFrame):\n",
" close_prices = df['Close'].iloc[:, 0] # Take first column if multiple\n",
" else:\n",
" close_prices = df['Close']\n",
" else:\n",
" # If Close column doesn't exist, skip this ticker\n",
" print(f\"Skipping {ticker} - no Close data\")\n",
" continue\n",
" \n",
" if 'High' in df.columns:\n",
" if isinstance(df['High'], pd.DataFrame):\n",
" high_prices = df['High'].iloc[:, 0] # Take first column if multiple\n",
" else:\n",
" high_prices = df['High']\n",
" else:\n",
" high_prices = close_prices # Fallback to close prices\n",
" \n",
" if 'Low' in df.columns:\n",
" if isinstance(df['Low'], pd.DataFrame):\n",
" low_prices = df['Low'].iloc[:, 0] # Take first column if multiple\n",
" else:\n",
" low_prices = df['Low']\n",
" else:\n",
" low_prices = close_prices # Fallback to close prices\n",
" \n",
" if 'Volume' in df.columns:\n",
" if isinstance(df['Volume'], pd.DataFrame):\n",
" volume_data = df['Volume'].iloc[:, 0] # Take first column if multiple\n",
" else:\n",
" volume_data = df['Volume']\n",
" else:\n",
" volume_data = pd.Series([1] * len(df), index=df.index) # Default volume\n",
" \n",
" # Calculate returns and technical indicators\n",
" returns = close_prices.pct_change()\n",
" volatility = returns.rolling(window=30).std()\n",
" ma_7 = close_prices.rolling(window=7).mean()\n",
" ma_30 = close_prices.rolling(window=30).mean()\n",
" \n",
" # Avoid division by zero\n",
" price_ma_ratio = np.where(ma_30 != 0, close_prices / ma_30, 1)\n",
" volume_ma = volume_data.rolling(window=30).mean()\n",
" volume_ratio = np.where(volume_ma != 0, volume_data / volume_ma, 1)\n",
" \n",
" # Get the latest data point for each cryptocurrency (avoid NaN values)\n",
" valid_indices = ~(returns.isna() | volatility.isna() | pd.Series(price_ma_ratio).isna() | pd.Series(volume_ratio).isna())\n",
" if valid_indices.sum() == 0:\n",
" continue\n",
" \n",
" latest_valid_idx = valid_indices[::-1].idxmax() # Last valid index\n",
" \n",
" features = {\n",
" 'Ticker': ticker,\n",
" 'Close_Price': float(close_prices.iloc[latest_valid_idx]),\n",
" 'Returns': float(returns.iloc[latest_valid_idx]),\n",
" 'Volatility': float(volatility.iloc[latest_valid_idx]),\n",
" 'Price_MA_Ratio': float(price_ma_ratio[latest_valid_idx]),\n",
" 'Volume_Ratio': float(volume_ratio[latest_valid_idx]),\n",
" 'High_Low_Ratio': float(high_prices.iloc[latest_valid_idx] / low_prices.iloc[latest_valid_idx]) if low_prices.iloc[latest_valid_idx] != 0 else 1.0\n",
" }\n",
" \n",
" features_list.append(features)\n",
" \n",
" # Store returns for similarity analysis (drop NaN values)\n",
" returns_clean = returns.dropna()\n",
" if len(returns_clean) > 0:\n",
" returns_list.append({\n",
" 'ticker': ticker,\n",
" 'returns': returns_clean,\n",
" 'mean_return': returns_clean.mean(),\n",
" 'std_return': returns_clean.std()\n",
" })\n",
" \n",
" except Exception as e:\n",
" print(f\"Error processing {ticker}: {str(e)}\")\n",
" continue\n",
" \n",
" self.features_df = pd.DataFrame(features_list)\n",
" self.returns_data = returns_list\n",
" \n",
" # Prepare numerical features for clustering and anomaly detection\n",
" self.numerical_features = ['Close_Price', 'Returns', 'Volatility', \n",
" 'Price_MA_Ratio', 'Volume_Ratio', 'High_Low_Ratio']\n",
" \n",
" # Remove rows with NaN values\n",
" self.features_df = self.features_df.dropna()\n",
" \n",
" print(f\"Data preprocessing completed. Processed {len(self.features_df)} cryptocurrencies\")\n",
" print(f\"Columns: {list(self.features_df.columns)}\")\n",
" return self.features_df \n",
"\n",
" def similarity_analysis(self):\n",
" \"\"\"\n",
" Perform similarity analysis between cryptocurrencies\n",
" \"\"\"\n",
" print(\"Performing similarity analysis...\")\n",
" \n",
" # Calculate correlation matrix based on returns\n",
" returns_df = pd.DataFrame()\n",
" for item in self.returns_data:\n",
" returns_df[item['ticker']] = item['returns'].tail(252) # Last year of data\n",
" \n",
" # Handle missing values by forward filling\n",
" returns_df = returns_df.fillna(method='ffill').fillna(method='bfill')\n",
" \n",
" # Calculate correlation matrix\n",
" self.correlation_matrix = returns_df.corr()\n",
" \n",
" # Display top similar pairs\n",
" print(\"Top similar cryptocurrency pairs (based on correlation):\")\n",
" similar_pairs = []\n",
" for i in range(len(self.correlation_matrix.columns)):\n",
" for j in range(i+1, len(self.correlation_matrix.columns)):\n",
" ticker1 = self.correlation_matrix.columns[i]\n",
" ticker2 = self.correlation_matrix.columns[j]\n",
" correlation = self.correlation_matrix.iloc[i, j]\n",
" similar_pairs.append((ticker1, ticker2, correlation))\n",
" \n",
" # Sort by correlation\n",
" similar_pairs.sort(key=lambda x: x[2], reverse=True)\n",
" \n",
" print(\"Top 10 most similar pairs:\")\n",
" for i, (t1, t2, corr) in enumerate(similar_pairs[:10]):\n",
" print(f\"{i+1}. {t1} - {t2}: {corr:.3f}\")\n",
" \n",
" # Visualize correlation matrix\n",
" plt.figure(figsize=(12, 10))\n",
" sns.heatmap(self.correlation_matrix, annot=True, cmap='coolwarm', center=0,\n",
" fmt='.2f', square=True)\n",
" plt.title('Cryptocurrency Returns Correlation Matrix')\n",
" plt.tight_layout()\n",
" plt.show()\n",
" \n",
" print(\"\\nSimilarity analysis completed\\n\")\n",
" return self.correlation_matrix\n",
" \n",
" def build_anomaly_detection_models(self):\n",
" \"\"\"\n",
" Build and train anomaly detection models\n",
" \"\"\"\n",
" print(\"Building anomaly detection models...\")\n",
" \n",
" # Prepare data for anomaly detection\n",
" X = self.features_df[self.numerical_features].values\n",
" X_scaled = self.scaler.fit_transform(X)\n",
" \n",
" # 1. K-Means Clustering for outlier detection\n",
" self.kmeans = KMeans(n_clusters=3, random_state=42)\n",
" cluster_labels = self.kmeans.fit_predict(X_scaled)\n",
" self.features_df['Cluster'] = cluster_labels\n",
" \n",
" # 2. Isolation Forest\n",
" self.isolation_forest = IsolationForest(contamination=0.1, random_state=42)\n",
" isolation_predictions = self.isolation_forest.fit_predict(X_scaled)\n",
" self.features_df['Isolation_Anomaly'] = isolation_predictions\n",
" \n",
" # 3. One-Class SVM\n",
" self.one_class_svm = OneClassSVM(nu=0.1)\n",
" svm_predictions = self.one_class_svm.fit_predict(X_scaled)\n",
" self.features_df['SVM_Anomaly'] = svm_predictions\n",
" \n",
" # Combine anomaly detection results\n",
" self.features_df['Anomaly_Score'] = (\n",
" (self.features_df['Isolation_Anomaly'] == -1).astype(int) +\n",
" (self.features_df['SVM_Anomaly'] == -1).astype(int)\n",
" )\n",
" \n",
" # Anomalies are detected if 2 or more models flag them\n",
" self.features_df['Is_Anomaly'] = self.features_df['Anomaly_Score'] >= 1\n",
" \n",
" print(\"Anomaly detection models built successfully\")\n",
" \n",
" # Display anomalies found\n",
" anomalies = self.features_df[self.features_df['Is_Anomaly']]\n",
" if len(anomalies) > 0:\n",
" print(f\"\\nDetected {len(anomalies)} potential anomalies:\")\n",
" for _, row in anomalies.iterrows():\n",
" print(f\" • {row['Ticker']}: Anomaly Score = {row['Anomaly_Score']}\")\n",
" else:\n",
" print(\"No anomalies detected in current data\")\n",
" \n",
" print(\"\\nModel building completed\\n\")\n",
" return self.features_df\n",
" \n",
" def detect_new_anomalies(self, new_data_point):\n",
" \"\"\"\n",
" Detect anomalies in new incoming data\n",
" \"\"\"\n",
" print(\"Detecting anomalies in new data...\")\n",
" \n",
" # Preprocess new data point (assuming it's in the same format)\n",
" new_scaled = self.scaler.transform([new_data_point])\n",
" \n",
" # Apply all models\n",
" kmeans_pred = self.kmeans.predict(new_scaled)[0]\n",
" isolation_pred = self.isolation_forest.predict(new_scaled)[0]\n",
" svm_pred = self.one_class_svm.predict(new_scaled)[0]\n",
" \n",
" # Calculate anomaly score\n",
" anomaly_score = (isolation_pred == -1) + (svm_pred == -1)\n",
" is_anomaly = anomaly_score >= 1\n",
" \n",
" result = {\n",
" 'Cluster': kmeans_pred,\n",
" 'Isolation_Prediction': 'Anomaly' if isolation_pred == -1 else 'Normal',\n",
" 'SVM_Prediction': 'Anomaly' if svm_pred == -1 else 'Normal',\n",
" 'Anomaly_Score': anomaly_score,\n",
" 'Is_Anomaly': is_anomaly\n",
" }\n",
" \n",
" print(f\"New data point analysis:\")\n",
" print(f\" Cluster: {result['Cluster']}\")\n",
" print(f\" Isolation Forest: {result['Isolation_Prediction']}\")\n",
" print(f\" One-Class SVM: {result['SVM_Prediction']}\")\n",
" print(f\" Overall: {'ANOMALY' if is_anomaly else 'NORMAL'}\")\n",
" \n",
" return result\n",
" \n",
" def visualize_results(self):\n",
" \"\"\"\n",
" Visualize the results of the analysis\n",
" \"\"\"\n",
" print(\"Generating visualizations...\")\n",
" \n",
" # Check what columns are actually available\n",
" print(f\"Available columns: {list(self.features_df.columns)}\")\n",
" \n",
" # 1. PCA visualization of clusters\n",
" X_scaled = self.scaler.transform(self.features_df[self.numerical_features])\n",
" X_pca = self.pca.fit_transform(X_scaled)\n",
" \n",
" plt.figure(figsize=(15, 5))\n",
" \n",
" # Plot 1: Clustering results\n",
" plt.subplot(1, 3, 1)\n",
" scatter = plt.scatter(X_pca[:, 0], X_pca[:, 1], c=self.features_df['Cluster'], \n",
" cmap='viridis', alpha=0.7)\n",
" plt.colorbar(scatter)\n",
" plt.title('Cryptocurrency Clustering (PCA)')\n",
" plt.xlabel('First Principal Component')\n",
" plt.ylabel('Second Principal Component')\n",
" \n",
" # Plot 2: Anomalies vs Normal points\n",
" plt.subplot(1, 3, 2)\n",
" colors = ['red' if x else 'blue' for x in self.features_df['Is_Anomaly']]\n",
" plt.scatter(X_pca[:, 0], X_pca[:, 1], c=colors, alpha=0.7)\n",
" plt.title('Anomaly Detection Results')\n",
" plt.xlabel('First Principal Component')\n",
" plt.ylabel('Second Principal Component')\n",
" \n",
" # Plot 3: Feature distributions - use actual available columns\n",
" plt.subplot(1, 3, 3)\n",
" # Check which numerical features are actually in the DataFrame\n",
" available_features = [col for col in ['Returns', 'Volatility'] if col in self.features_df.columns]\n",
" if not available_features:\n",
" # Try alternative column names that might be present\n",
" available_features = [col for col in self.numerical_features if col in self.features_df.columns][:2]\n",
" \n",
" if available_features:\n",
" self.features_df.boxplot(column=available_features, ax=plt.gca())\n",
" plt.title('Feature Distribution')\n",
" plt.xticks(rotation=45)\n",
" else:\n",
" plt.title('No suitable features found for boxplot')\n",
" plt.text(0.5, 0.5, 'No data available', ha='center', va='center')\n",
" \n",
" plt.tight_layout()\n",
" plt.show()\n",
" \n",
" print(\"Visualizations completed\\n\") \n",
" def generate_report(self):\n",
" \"\"\"\n",
" Generate a comprehensive report of the analysis\n",
" \"\"\"\n",
" print(\"=\"*60)\n",
" print(\"CRYPTOCURRENCY ANALYSIS REPORT\")\n",
" print(\"=\"*60)\n",
" \n",
" print(f\"\\n1. DATA SUMMARY:\")\n",
" print(f\" • Total cryptocurrencies analyzed: {len(self.features_df)}\")\n",
" print(f\" • Time period: 1 year\")\n",
" print(f\" • Features analyzed: {', '.join(self.numerical_features)}\")\n",
" \n",
" print(f\"\\n2. SIMILARITY ANALYSIS:\")\n",
" print(f\" • Correlation matrix generated for all pairs\")\n",
" print(f\" • Top similar pairs identified\")\n",
" \n",
" print(f\"\\n3. ANOMALY DETECTION:\")\n",
" anomalies = self.features_df[self.features_df['Is_Anomaly']]\n",
" print(f\" • Anomalies detected: {len(anomalies)}\")\n",
" if len(anomalies) > 0:\n",
" for _, row in anomalies.iterrows():\n",
" print(f\" - {row['Ticker']}\")\n",
" \n",
" print(f\"\\n4. CLUSTERING:\")\n",
" cluster_counts = self.features_df['Cluster'].value_counts()\n",
" for cluster, count in cluster_counts.items():\n",
" print(f\" • Cluster {cluster}: {count} cryptocurrencies\")\n",
" \n",
" print(\"=\"*60)\n",
"\n",
" def generate_report(self):\n",
" \"\"\"\n",
" Generate a comprehensive report of the analysis\n",
" \"\"\"\n",
" print(\"=\"*60)\n",
" print(\"CRYPTOCURRENCY ANALYSIS REPORT\")\n",
" print(\"=\"*60)\n",
" \n",
" print(f\"\\n1. DATA SUMMARY:\")\n",
" print(f\" • Total cryptocurrencies analyzed: {len(self.features_df)}\")\n",
" print(f\" • Time period: 1 year\")\n",
" print(f\" • Features analyzed: {', '.join(self.numerical_features)}\")\n",
" \n",
" print(f\"\\n2. SIMILARITY ANALYSIS:\")\n",
" print(f\" • Correlation matrix generated for all pairs\")\n",
" print(f\" • Top similar pairs identified\")\n",
" \n",
" print(f\"\\n3. ANOMALY DETECTION:\")\n",
" anomalies = self.features_df[self.features_df['Is_Anomaly']]\n",
" print(f\" • Anomalies detected: {len(anomalies)}\")\n",
" if len(anomalies) > 0:\n",
" for _, row in anomalies.iterrows():\n",
" print(f\" - {row['Ticker']}\")\n",
" \n",
" print(f\"\\n4. CLUSTERING:\")\n",
" cluster_counts = self.features_df['Cluster'].value_counts()\n",
" for cluster, count in cluster_counts.items():\n",
" print(f\" • Cluster {cluster}: {count} cryptocurrencies\")\n",
" \n",
" print(\"=\"*60)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "2c4bdc02",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[*********************100%***********************] 1 of 1 completed"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Downloading cryptocurrency data...\n",
"✓ Downloaded data for BTC-USD\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"✓ Downloaded data for ETH-USD\n",
"✓ Downloaded data for BNB-USD\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"✓ Downloaded data for XRP-USD\n",
"✓ Downloaded data for ADA-USD\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[*********************100%***********************] 1 of 1 completed\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"✓ Downloaded data for DOGE-USD\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"✓ Downloaded data for SOL-USD\n",
"✓ Downloaded data for DOT-USD\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"✓ Downloaded data for MATIC-USD\n",
"✓ Downloaded data for LTC-USD\n",
"✓ Downloaded data for SHIB-USD\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"✓ Downloaded data for TRX-USD\n",
"✓ Downloaded data for AVAX-USD\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"✓ Downloaded data for UNI-USD\n",
"✓ Downloaded data for LINK-USD\n",
"Successfully downloaded data for 15 cryptocurrencies\n",
"\n",
"Preprocessing data...\n",
"Data preprocessing completed. Processed 15 cryptocurrencies\n",
"Columns: ['Ticker', 'Close_Price', 'Returns', 'Volatility', 'Price_MA_Ratio', 'Volume_Ratio', 'High_Low_Ratio']\n"
]
},
{
"data": {
"application/vnd.microsoft.datawrangler.viewer.v0+json": {
"columns": [
{
"name": "index",
"rawType": "int64",
"type": "integer"
},
{
"name": "Ticker",
"rawType": "object",
"type": "string"
},
{
"name": "Close_Price",
"rawType": "float64",
"type": "float"
},
{
"name": "Returns",
"rawType": "float64",
"type": "float"
},
{
"name": "Volatility",
"rawType": "float64",
"type": "float"
},
{
"name": "Price_MA_Ratio",
"rawType": "float64",
"type": "float"
},
{
"name": "Volume_Ratio",
"rawType": "float64",
"type": "float"
},
{
"name": "High_Low_Ratio",
"rawType": "float64",
"type": "float"
}
],
"ref": "14566d31-ca6e-4da1-9122-4b7c7d1a6675",
"rows": [
[
"0",
"BTC-USD",
"117824.9296875",
"-0.04474583292162926",
"0.014816652681393472",
"1.0028592148405697",
"1.5821444699675502",
"1.0555415139433872"
],
[
"1",
"ETH-USD",
"4554.04150390625",
"-0.04251947955687252",
"0.03589733980318593",
"1.1880576114143897",
"1.900801548927478",
"1.0652001173964085"
],
[
"2",
"BNB-USD",
"844.2289428710938",
"-0.005626053460699776",
"0.021508748314019423",
"1.0806753686355166",
"1.5330639661575336",
"1.0461425370704636"
],
[
"3",
"XRP-USD",
"3.0665361881256104",
"-0.0652488597941423",
"0.04908735345401255",
"0.9615329697196453",
"1.392011587352721",
"1.0905490870965873"
],
[
"4",
"ADA-USD",
"0.9057555198669434",
"-0.00018600051069539436",
"0.04048090524972863",
"1.1309264128631853",
"3.7152840360972452",
"1.121537325211226"
],
[
"5",
"DOGE-USD",
"0.22310678660869598",
"-0.09011026769121644",
"0.055321487882966515",
"0.9773637281703155",
"1.5722847495345496",
"1.1390006293562114"
],
[
"6",
"SOL-USD",
"192.34945678710938",
"-0.04584030646190462",
"0.04128588106875424",
"1.0696208095855866",
"2.0022315688410655",
"1.0928768889485414"
],
[
"7",
"DOT-USD",
"3.979785680770874",
"-0.0705317966581882",
"0.039267691800707064",
"0.9906510874880544",
"1.6146763262546098",
"1.0967155418256935"
],
[
"8",
"MATIC-USD",
"0.21641500294208527",
"0.017332035858389272",
"0.048650857498484294",
"0.9070045458086071",
"0.10956768455503935",
"1.0316135935753004"
],
[
"9",
"LTC-USD",
"121.77552032470703",
"-0.07025288945538821",
"0.04182372909893931",
"1.0601149629853501",
"1.2187182737724183",
"1.0978056204706301"
],
[
"10",
"SHIB-USD",
"1.2865454664279241e-05",
"-0.08103896515615405",
"0.04987858265438886",
"0.9486272014789492",
"1.3320674198014906",
"1.1014073729878804"
],
[
"11",
"TRX-USD",
"0.3597746193408966",
"-0.007077269361385086",
"0.017728202921838947",
"1.0953633004447287",
"1.8675173093200668",
"1.032972820087163"
],
[
"12",
"AVAX-USD",
"23.685495376586914",
"-0.07229345359880124",
"0.04174425989332199",
"0.9982935570627587",
"1.6171175077833786",
"1.1009876347118317"
],
[
"13",
"UNI-USD",
"0.0001630000042496249",
"0.0",
"0.02785314422168725",
"0.9780000188942066",
"0.0",
"1.0"
],
[
"14",
"LINK-USD",
"22.58526039123535",
"-0.05897844496757054",
"0.05153772040459448",
"1.2016823376755383",
"2.0551558907596466",
"1.0949510707579013"
]
],
"shape": {
"columns": 7,
"rows": 15
}
},
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Ticker | \n",
" Close_Price | \n",
" Returns | \n",
" Volatility | \n",
" Price_MA_Ratio | \n",
" Volume_Ratio | \n",
" High_Low_Ratio | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" BTC-USD | \n",
" 117824.929688 | \n",
" -0.044746 | \n",
" 0.014817 | \n",
" 1.002859 | \n",
" 1.582144 | \n",
" 1.055542 | \n",
"
\n",
" \n",
" | 1 | \n",
" ETH-USD | \n",
" 4554.041504 | \n",
" -0.042519 | \n",
" 0.035897 | \n",
" 1.188058 | \n",
" 1.900802 | \n",
" 1.065200 | \n",
"
\n",
" \n",
" | 2 | \n",
" BNB-USD | \n",
" 844.228943 | \n",
" -0.005626 | \n",
" 0.021509 | \n",
" 1.080675 | \n",
" 1.533064 | \n",
" 1.046143 | \n",
"
\n",
" \n",
" | 3 | \n",
" XRP-USD | \n",
" 3.066536 | \n",
" -0.065249 | \n",
" 0.049087 | \n",
" 0.961533 | \n",
" 1.392012 | \n",
" 1.090549 | \n",
"
\n",
" \n",
" | 4 | \n",
" ADA-USD | \n",
" 0.905756 | \n",
" -0.000186 | \n",
" 0.040481 | \n",
" 1.130926 | \n",
" 3.715284 | \n",
" 1.121537 | \n",
"
\n",
" \n",
" | 5 | \n",
" DOGE-USD | \n",
" 0.223107 | \n",
" -0.090110 | \n",
" 0.055321 | \n",
" 0.977364 | \n",
" 1.572285 | \n",
" 1.139001 | \n",
"
\n",
" \n",
" | 6 | \n",
" SOL-USD | \n",
" 192.349457 | \n",
" -0.045840 | \n",
" 0.041286 | \n",
" 1.069621 | \n",
" 2.002232 | \n",
" 1.092877 | \n",
"
\n",
" \n",
" | 7 | \n",
" DOT-USD | \n",
" 3.979786 | \n",
" -0.070532 | \n",
" 0.039268 | \n",
" 0.990651 | \n",
" 1.614676 | \n",
" 1.096716 | \n",
"
\n",
" \n",
" | 8 | \n",
" MATIC-USD | \n",
" 0.216415 | \n",
" 0.017332 | \n",
" 0.048651 | \n",
" 0.907005 | \n",
" 0.109568 | \n",
" 1.031614 | \n",
"
\n",
" \n",
" | 9 | \n",
" LTC-USD | \n",
" 121.775520 | \n",
" -0.070253 | \n",
" 0.041824 | \n",
" 1.060115 | \n",
" 1.218718 | \n",
" 1.097806 | \n",
"
\n",
" \n",
" | 10 | \n",
" SHIB-USD | \n",
" 0.000013 | \n",
" -0.081039 | \n",
" 0.049879 | \n",
" 0.948627 | \n",
" 1.332067 | \n",
" 1.101407 | \n",
"
\n",
" \n",
" | 11 | \n",
" TRX-USD | \n",
" 0.359775 | \n",
" -0.007077 | \n",
" 0.017728 | \n",
" 1.095363 | \n",
" 1.867517 | \n",
" 1.032973 | \n",
"
\n",
" \n",
" | 12 | \n",
" AVAX-USD | \n",
" 23.685495 | \n",
" -0.072293 | \n",
" 0.041744 | \n",
" 0.998294 | \n",
" 1.617118 | \n",
" 1.100988 | \n",
"
\n",
" \n",
" | 13 | \n",
" UNI-USD | \n",
" 0.000163 | \n",
" 0.000000 | \n",
" 0.027853 | \n",
" 0.978000 | \n",
" 0.000000 | \n",
" 1.000000 | \n",
"
\n",
" \n",
" | 14 | \n",
" LINK-USD | \n",
" 22.585260 | \n",
" -0.058978 | \n",
" 0.051538 | \n",
" 1.201682 | \n",
" 2.055156 | \n",
" 1.094951 | \n",
"
\n",
" \n",
"
\n",
"
"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Similarity analysis completed\n",
"\n"
]
},
{
"data": {
"application/vnd.microsoft.datawrangler.viewer.v0+json": {
"columns": [
{
"name": "index",
"rawType": "object",
"type": "string"
},
{
"name": "BTC-USD",
"rawType": "float64",
"type": "float"
},
{
"name": "ETH-USD",
"rawType": "float64",
"type": "float"
},
{
"name": "BNB-USD",
"rawType": "float64",
"type": "float"
},
{
"name": "XRP-USD",
"rawType": "float64",
"type": "float"
},
{
"name": "ADA-USD",
"rawType": "float64",
"type": "float"
},
{
"name": "DOGE-USD",
"rawType": "float64",
"type": "float"
},
{
"name": "SOL-USD",
"rawType": "float64",
"type": "float"
},
{
"name": "DOT-USD",
"rawType": "float64",
"type": "float"
},
{
"name": "MATIC-USD",
"rawType": "float64",
"type": "float"
},
{
"name": "LTC-USD",
"rawType": "float64",
"type": "float"
},
{
"name": "SHIB-USD",
"rawType": "float64",
"type": "float"
},
{
"name": "TRX-USD",
"rawType": "float64",
"type": "float"
},
{
"name": "AVAX-USD",
"rawType": "float64",
"type": "float"
},
{
"name": "UNI-USD",
"rawType": "float64",
"type": "float"
},
{
"name": "LINK-USD",
"rawType": "float64",
"type": "float"
}
],
"ref": "f6254143-d9d4-4b41-b99e-6b96b28f9921",
"rows": [
[
"BTC-USD",
"1.0",
"0.7986424625734226",
"0.6482793033275979",
"0.7456600754365267",
"0.7164041686332907",
"0.7964835956476696",
"0.77321501194442",
"0.7183044145213001",
"0.5602219226808562",
"0.6327942217094216",
"0.627954215455201",
"0.46066350815518653",
"0.7737155206587835",
"0.8481508042829294",
"0.7616461148573074"
],
[
"ETH-USD",
"0.7986424625734226",
"1.0",
"0.7080973359115158",
"0.7036923510655948",
"0.7223418949594257",
"0.8512417824394078",
"0.7546582292786561",
"0.8187538089018461",
"0.5551541335182335",
"0.6646506737200718",
"0.7039743632665664",
"0.49901043905577946",
"0.8425526680204218",
"0.6312507153202408",
"0.838557020254197"
],
[
"BNB-USD",
"0.6482793033275979",
"0.7080973359115158",
"1.0",
"0.5881147557978883",
"0.5558375132245228",
"0.7093528958561227",
"0.635947896797573",
"0.7327382694029546",
"0.5896579782755974",
"0.6016640831886629",
"0.6196672565006741",
"0.48640960306278375",
"0.7274044533976",
"0.5394397426149486",
"0.6643609689924808"
],
[
"XRP-USD",
"0.7456600754365267",
"0.7036923510655948",
"0.5881147557978883",
"1.0",
"0.8199212572610615",
"0.7451790225147978",
"0.7466198228573968",
"0.69951857371863",
"0.5253139668121019",
"0.6111847496629687",
"0.563438378223815",
"0.45166451634514226",
"0.7181714515893987",
"0.6776447465435471",
"0.7227360251427635"
],
[
"ADA-USD",
"0.7164041686332907",
"0.7223418949594257",
"0.5558375132245228",
"0.8199212572610615",
"1.0",
"0.7213673847437885",
"0.7433675424261186",
"0.7042616559570198",
"0.5404521421648192",
"0.5273739397731345",
"0.5465266866779759",
"0.4340845220729991",
"0.7260259587257181",
"0.6452985428025357",
"0.7247690895720935"
],
[
"DOGE-USD",
"0.7964835956476696",
"0.8512417824394078",
"0.7093528958561227",
"0.7451790225147978",
"0.7213673847437885",
"1.0",
"0.7682595297571897",
"0.8448964816882972",
"0.582854123618813",
"0.7117368606484374",
"0.784313132707619",
"0.4791645284310745",
"0.8557518301501088",
"0.6338616300451798",
"0.8062160768363056"
],
[
"SOL-USD",
"0.77321501194442",
"0.7546582292786561",
"0.635947896797573",
"0.7466198228573968",
"0.7433675424261186",
"0.7682595297571897",
"1.0",
"0.7133529259347067",
"0.5102213425652745",
"0.5834087305672582",
"0.6144104831912715",
"0.42363780807723983",
"0.7713126731297596",
"0.6675466846964514",
"0.7450719000236465"
],
[
"DOT-USD",
"0.7183044145213001",
"0.8187538089018461",
"0.7327382694029546",
"0.69951857371863",
"0.7042616559570198",
"0.8448964816882972",
"0.7133529259347067",
"1.0",
"0.647433589856745",
"0.7609030796630218",
"0.768155108686504",
"0.5485412868327708",
"0.8866944699978591",
"0.5606883526297542",
"0.8205755386404796"
],
[
"MATIC-USD",
"0.5602219226808562",
"0.5551541335182335",
"0.5896579782755974",
"0.5253139668121019",
"0.5404521421648192",
"0.582854123618813",
"0.5102213425652745",
"0.647433589856745",
"1.0",
"0.5443387760307119",
"0.5276784037345296",
"0.5548382891944527",
"0.6332621152220875",
"0.6212109383568786",
"0.5910813082259896"
],
[
"LTC-USD",
"0.6327942217094216",
"0.6646506737200718",
"0.6016640831886629",
"0.6111847496629687",
"0.5273739397731345",
"0.7117368606484374",
"0.5834087305672582",
"0.7609030796630218",
"0.5443387760307119",
"1.0",
"0.5892728212071285",
"0.4971862140213053",
"0.7341582672533169",
"0.5159988617805904",
"0.6777651290403195"
],
[
"SHIB-USD",
"0.627954215455201",
"0.7039743632665664",
"0.6196672565006741",
"0.563438378223815",
"0.5465266866779759",
"0.784313132707619",
"0.6144104831912715",
"0.768155108686504",
"0.5276784037345296",
"0.5892728212071285",
"1.0",
"0.46869574186193314",
"0.7455375583586505",
"0.4802853364528364",
"0.6721688575838792"
],
[
"TRX-USD",
"0.46066350815518653",
"0.49901043905577946",
"0.48640960306278375",
"0.45166451634514226",
"0.4340845220729991",
"0.4791645284310745",
"0.42363780807723983",
"0.5485412868327708",
"0.5548382891944527",
"0.4971862140213053",
"0.46869574186193314",
"1.0",
"0.5294330496856146",
"0.42714342335871036",
"0.5151566393285687"
],
[
"AVAX-USD",
"0.7737155206587835",
"0.8425526680204218",
"0.7274044533976",
"0.7181714515893987",
"0.7260259587257181",
"0.8557518301501088",
"0.7713126731297596",
"0.8866944699978591",
"0.6332621152220875",
"0.7341582672533169",
"0.7455375583586505",
"0.5294330496856146",
"1.0",
"0.6208942764071217",
"0.8760414947974908"
],
[
"UNI-USD",
"0.8481508042829294",
"0.6312507153202408",
"0.5394397426149486",
"0.6776447465435471",
"0.6452985428025357",
"0.6338616300451798",
"0.6675466846964514",
"0.5606883526297542",
"0.6212109383568786",
"0.5159988617805904",
"0.4802853364528364",
"0.42714342335871036",
"0.6208942764071217",
"1.0",
"0.6375663206269536"
],
[
"LINK-USD",
"0.7616461148573074",
"0.838557020254197",
"0.6643609689924808",
"0.7227360251427635",
"0.7247690895720935",
"0.8062160768363056",
"0.7450719000236465",
"0.8205755386404796",
"0.5910813082259896",
"0.6777651290403195",
"0.6721688575838792",
"0.5151566393285687",
"0.8760414947974908",
"0.6375663206269536",
"1.0"
]
],
"shape": {
"columns": 15,
"rows": 15
}
},
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" BTC-USD | \n",
" ETH-USD | \n",
" BNB-USD | \n",
" XRP-USD | \n",
" ADA-USD | \n",
" DOGE-USD | \n",
" SOL-USD | \n",
" DOT-USD | \n",
" MATIC-USD | \n",
" LTC-USD | \n",
" SHIB-USD | \n",
" TRX-USD | \n",
" AVAX-USD | \n",
" UNI-USD | \n",
" LINK-USD | \n",
"
\n",
" \n",
" \n",
" \n",
" | BTC-USD | \n",
" 1.000000 | \n",
" 0.798642 | \n",
" 0.648279 | \n",
" 0.745660 | \n",
" 0.716404 | \n",
" 0.796484 | \n",
" 0.773215 | \n",
" 0.718304 | \n",
" 0.560222 | \n",
" 0.632794 | \n",
" 0.627954 | \n",
" 0.460664 | \n",
" 0.773716 | \n",
" 0.848151 | \n",
" 0.761646 | \n",
"
\n",
" \n",
" | ETH-USD | \n",
" 0.798642 | \n",
" 1.000000 | \n",
" 0.708097 | \n",
" 0.703692 | \n",
" 0.722342 | \n",
" 0.851242 | \n",
" 0.754658 | \n",
" 0.818754 | \n",
" 0.555154 | \n",
" 0.664651 | \n",
" 0.703974 | \n",
" 0.499010 | \n",
" 0.842553 | \n",
" 0.631251 | \n",
" 0.838557 | \n",
"
\n",
" \n",
" | BNB-USD | \n",
" 0.648279 | \n",
" 0.708097 | \n",
" 1.000000 | \n",
" 0.588115 | \n",
" 0.555838 | \n",
" 0.709353 | \n",
" 0.635948 | \n",
" 0.732738 | \n",
" 0.589658 | \n",
" 0.601664 | \n",
" 0.619667 | \n",
" 0.486410 | \n",
" 0.727404 | \n",
" 0.539440 | \n",
" 0.664361 | \n",
"
\n",
" \n",
" | XRP-USD | \n",
" 0.745660 | \n",
" 0.703692 | \n",
" 0.588115 | \n",
" 1.000000 | \n",
" 0.819921 | \n",
" 0.745179 | \n",
" 0.746620 | \n",
" 0.699519 | \n",
" 0.525314 | \n",
" 0.611185 | \n",
" 0.563438 | \n",
" 0.451665 | \n",
" 0.718171 | \n",
" 0.677645 | \n",
" 0.722736 | \n",
"
\n",
" \n",
" | ADA-USD | \n",
" 0.716404 | \n",
" 0.722342 | \n",
" 0.555838 | \n",
" 0.819921 | \n",
" 1.000000 | \n",
" 0.721367 | \n",
" 0.743368 | \n",
" 0.704262 | \n",
" 0.540452 | \n",
" 0.527374 | \n",
" 0.546527 | \n",
" 0.434085 | \n",
" 0.726026 | \n",
" 0.645299 | \n",
" 0.724769 | \n",
"
\n",
" \n",
" | DOGE-USD | \n",
" 0.796484 | \n",
" 0.851242 | \n",
" 0.709353 | \n",
" 0.745179 | \n",
" 0.721367 | \n",
" 1.000000 | \n",
" 0.768260 | \n",
" 0.844896 | \n",
" 0.582854 | \n",
" 0.711737 | \n",
" 0.784313 | \n",
" 0.479165 | \n",
" 0.855752 | \n",
" 0.633862 | \n",
" 0.806216 | \n",
"
\n",
" \n",
" | SOL-USD | \n",
" 0.773215 | \n",
" 0.754658 | \n",
" 0.635948 | \n",
" 0.746620 | \n",
" 0.743368 | \n",
" 0.768260 | \n",
" 1.000000 | \n",
" 0.713353 | \n",
" 0.510221 | \n",
" 0.583409 | \n",
" 0.614410 | \n",
" 0.423638 | \n",
" 0.771313 | \n",
" 0.667547 | \n",
" 0.745072 | \n",
"
\n",
" \n",
" | DOT-USD | \n",
" 0.718304 | \n",
" 0.818754 | \n",
" 0.732738 | \n",
" 0.699519 | \n",
" 0.704262 | \n",
" 0.844896 | \n",
" 0.713353 | \n",
" 1.000000 | \n",
" 0.647434 | \n",
" 0.760903 | \n",
" 0.768155 | \n",
" 0.548541 | \n",
" 0.886694 | \n",
" 0.560688 | \n",
" 0.820576 | \n",
"
\n",
" \n",
" | MATIC-USD | \n",
" 0.560222 | \n",
" 0.555154 | \n",
" 0.589658 | \n",
" 0.525314 | \n",
" 0.540452 | \n",
" 0.582854 | \n",
" 0.510221 | \n",
" 0.647434 | \n",
" 1.000000 | \n",
" 0.544339 | \n",
" 0.527678 | \n",
" 0.554838 | \n",
" 0.633262 | \n",
" 0.621211 | \n",
" 0.591081 | \n",
"
\n",
" \n",
" | LTC-USD | \n",
" 0.632794 | \n",
" 0.664651 | \n",
" 0.601664 | \n",
" 0.611185 | \n",
" 0.527374 | \n",
" 0.711737 | \n",
" 0.583409 | \n",
" 0.760903 | \n",
" 0.544339 | \n",
" 1.000000 | \n",
" 0.589273 | \n",
" 0.497186 | \n",
" 0.734158 | \n",
" 0.515999 | \n",
" 0.677765 | \n",
"
\n",
" \n",
" | SHIB-USD | \n",
" 0.627954 | \n",
" 0.703974 | \n",
" 0.619667 | \n",
" 0.563438 | \n",
" 0.546527 | \n",
" 0.784313 | \n",
" 0.614410 | \n",
" 0.768155 | \n",
" 0.527678 | \n",
" 0.589273 | \n",
" 1.000000 | \n",
" 0.468696 | \n",
" 0.745538 | \n",
" 0.480285 | \n",
" 0.672169 | \n",
"
\n",
" \n",
" | TRX-USD | \n",
" 0.460664 | \n",
" 0.499010 | \n",
" 0.486410 | \n",
" 0.451665 | \n",
" 0.434085 | \n",
" 0.479165 | \n",
" 0.423638 | \n",
" 0.548541 | \n",
" 0.554838 | \n",
" 0.497186 | \n",
" 0.468696 | \n",
" 1.000000 | \n",
" 0.529433 | \n",
" 0.427143 | \n",
" 0.515157 | \n",
"
\n",
" \n",
" | AVAX-USD | \n",
" 0.773716 | \n",
" 0.842553 | \n",
" 0.727404 | \n",
" 0.718171 | \n",
" 0.726026 | \n",
" 0.855752 | \n",
" 0.771313 | \n",
" 0.886694 | \n",
" 0.633262 | \n",
" 0.734158 | \n",
" 0.745538 | \n",
" 0.529433 | \n",
" 1.000000 | \n",
" 0.620894 | \n",
" 0.876041 | \n",
"
\n",
" \n",
" | UNI-USD | \n",
" 0.848151 | \n",
" 0.631251 | \n",
" 0.539440 | \n",
" 0.677645 | \n",
" 0.645299 | \n",
" 0.633862 | \n",
" 0.667547 | \n",
" 0.560688 | \n",
" 0.621211 | \n",
" 0.515999 | \n",
" 0.480285 | \n",
" 0.427143 | \n",
" 0.620894 | \n",
" 1.000000 | \n",
" 0.637566 | \n",
"
\n",
" \n",
" | LINK-USD | \n",
" 0.761646 | \n",
" 0.838557 | \n",
" 0.664361 | \n",
" 0.722736 | \n",
" 0.724769 | \n",
" 0.806216 | \n",
" 0.745072 | \n",
" 0.820576 | \n",
" 0.591081 | \n",
" 0.677765 | \n",
" 0.672169 | \n",
" 0.515157 | \n",
" 0.876041 | \n",
" 0.637566 | \n",
" 1.000000 | \n",
"
\n",
" \n",
"
\n",
"